© 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. 218828
    Prev
    Next
    INDEX
    Explanations

    injury, suffers, damage, rot

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

    alternatives or suggestions

    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
     festivals
    0.43
    ?
    0.42
    ,
    0.39
     ellipsoid
    0.39
     McGill
    0.38
    +
    0.38
     Israel
    0.37
     تدخل
    0.37
     부터
    0.37
     री
    0.37
    POSITIVE LOGITS
    ढ़े
    0.50
     Wilk
    0.50
    ढ़े
    0.46
    ính
    0.46
    owy
    0.46
     feita
    0.46
    FAPI
    0.45
    𝓊
    0.45
     equipado
    0.45
    Comic
    0.45
    Activations Density 0.000%

    No Known Activations