© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3320
    Prev
    Next
    INDEX
    Explanations

    code comments and symbols

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

    /* comments */

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     polyphen
    0.52
     dechlor
    0.51
     oxígeno
    0.51
     organismo
    0.50
     آهن
    0.50
    鰹
    0.50
     क्लोरीन
    0.49
     হাইড্রোজেন
    0.49
    鹸
    0.49
     vidé
    0.49
    POSITIVE LOGITS
    id
    0.66
    ’
    0.65
    <0x0D>
    0.64
    re
    0.60
    un
    0.57
    all
    0.57
    st
    0.57
    use
    0.57
    ola
    0.57
    ul
    0.56
    Activations Density 0.000%

    No Known Activations