© 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. 99235
    Prev
    Next
    INDEX
    Explanations

    payment caps

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

    describing quantities or levels

    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
    iping
    0.46
    GraphQL
    0.46
    坚定
    0.44
    激动
    0.43
    inosaur
    0.43
    SetConfig
    0.43
    骁
    0.42
    Electrical
    0.42
     dying
    0.42
    欢
    0.42
    POSITIVE LOGITS
     इंडियन
    0.49
    ب
    0.48
     करावा
    0.46
     යන
    0.45
     ഇന്ത്യൻ
    0.44
     dieser
    0.43
     espè
    0.43
     accorded
    0.43
     proizvođa
    0.43
    ណា
    0.42
    Activations Density 0.001%

    No Known Activations