© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8943
    Prev
    Next
    INDEX
    Explanations

    seeking reassurance or control

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is detecting numeric quantities or measurements (tokens representing numbers or metrics).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    language describing manipulative, deceptive, or illegitimate actions and schemes.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    statements alleging or arguing about misconduct, bias, or wrongdoing in legal, political, or organizational contexts, especially in formal, abstract, argumentative prose.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Finances
    0.66
    hrad
    0.60
     தெளிவாக
    0.60
     peacefully
    0.57
     স্পষ্টভাবে
    0.57
     এতটা
    0.56
     たら
    0.55
    üdis
    0.55
    τας
    0.54
    冽
    0.54
    POSITIVE LOGITS
     fanciful
    0.93
     arbitrarily
    0.92
     pseudo
    0.89
     exaggerated
    0.86
     unjustified
    0.84
     exaggerate
    0.84
     arbitrary
    0.84
     convenient
    0.83
     spurious
    0.82
     artificially
    0.80
    Activations Density 0.315%

    No Known Activations