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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10652
    Prev
    Next
    INDEX
    Explanations

    estimate, roughly, common rule

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    hasil
    0.57
     feitos
    0.56
     செய்க
    0.56
    吽
    0.56
    썼
    0.55
    फाइनल
    0.54
     принял
    0.54
     কৰি
    0.54
    endering
    0.53
     newcom
    0.53
    POSITIVE LOGITS
    </h4>
    0.69
     EXACT
    0.57
     tén
    0.54
    Fan
    0.53
     Tige
    0.53
     Uw
    0.53
    ATION
    0.52
    举
    0.52
     radionuclide
    0.52
     οδηγ
    0.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.