© 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. 537
    Prev
    Next
    INDEX
    Explanations

    categories, items, concepts

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

    listing diverse 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
     thefe
    0.30
     această
    0.30
     épisode
    0.28
    <unused1>
    0.28
     három
    0.28
     Nure
    0.27
     najważ
    0.27
     Gün
    0.27
     tých
    0.27
     dieser
    0.27
    POSITIVE LOGITS
    、
    0.33
    或
    0.31
    や
    0.30
     или
    0.29
    ла
    0.28
    ד
    0.27
    ;
    0.27
     и
    0.27
    я
    0.27
    丶
    0.26
    Activations Density 0.419%

    No Known Activations