© 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. 7684
    Prev
    Next
    INDEX
    Explanations

    approximately or nearly

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

    The neuron does not activate on any tokens, indicating it isn’t detecting any pattern in these examples.

    oai_token-act-pair · o4-miniTriggered 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
     விதிக்க
    0.58
     []);
    0.56
     මු
    0.55
     otomatis
    0.55
     प्रचलित
    0.55
    סק
    0.54
     enfin
    0.54
     उत्तराखंड
    0.53
     অর্থাৎ
    0.52
     japonais
    0.52
    POSITIVE LOGITS
    约
    0.68
    years
    0.63
    approx
    0.62
    差不多
    0.61
    개월
    0.59
     約
    0.59
    nearly
    0.59
     yrs
    0.59
    approximately
    0.59
     years
    0.58
    Activations Density 0.000%

    No Known Activations