© 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. 116127
    Prev
    Next
    INDEX
    Explanations

    franchises, model, contacts, thing, equity, series

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

    constructing or transformation

    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
     in
    0.85
    in
    0.61
    在
    0.55
    In
    0.53
    s
    0.53
     over
    0.51
     because
    0.51
    ใน
    0.50
     as
    0.50
    a
    0.47
    POSITIVE LOGITS
     miei
    0.54
    矾
    0.52
    骖
    0.50
     garantiza
    0.48
    凌晨
    0.48
     серию
    0.48
    保证金
    0.46
    ㄵ
    0.46
     సా
    0.46
     Haha
    0.46
    Activations Density 0.000%

    No Known Activations