© 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. 122121
    Prev
    Next
    INDEX
    Explanations

    black carpet

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

    ranking or listing items

    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
    פת
    0.49
     Chakraborty
    0.46
     TUM
    0.46
    s
    0.45
    getDouble
    0.45
    මෙ
    0.45
     Calcutta
    0.43
    Chairman
    0.43
    <strong>
    0.43
     USDT
    0.43
    POSITIVE LOGITS
     necesidades
    0.52
     respiratoires
    0.51
     matière
    0.48
     espécies
    0.48
     odbior
    0.48
    yw
    0.47
     essentielle
    0.47
     actitudes
    0.47
     procès
    0.47
     prothorax
    0.47
    Activations Density 0.000%

    No Known Activations