© 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. 24-GEMMASCOPE-2-RES-16K
    7. 4262
    Prev
    Next
    INDEX
    Explanations

    dialog, novice, manager, owner, user, withdraw

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

    The neuron activates strongly on past‐tense or past‐participle forms (including equivalent suffixes in other languages).

    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_24_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
     unfolds
    0.89
    Além
    0.84
    །
    0.80
     unfolded
    0.80
    Half
    0.70
    ブレー
    0.70
     unfold
    0.69
    ２
    0.69
    Pull
    0.69
    Ple
    0.69
    POSITIVE LOGITS
    ed
    0.88
    endix
    0.87
    risi
    0.87
    okhlov
    0.86
    ت
    0.86
    isé
    0.85
     Monro
    0.85
     adott
    0.84
    ł
    0.83
     risiko
    0.82
    Activations Density 0.001%

    No Known Activations