© 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. 58794
    Prev
    Next
    INDEX
    Explanations

    great deal, we've got

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

    parts of words

    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
    V
    0.53
    H
    0.50
    E
    0.48
    R
    0.47
    в
    0.46
    Os
    0.45
    ими
    0.45
    Em
    0.44
    א
    0.44
    C
    0.44
    POSITIVE LOGITS
     gacch
    0.56
     abide
    0.56
     nCenters
    0.55
    ン
    0.52
     ダイヤモンド
    0.50
     testacé
    0.50
     coqu
    0.48
     becom
    0.48
     despise
    0.48
     関係
    0.48
    Activations Density 0.000%

    No Known Activations