© 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. 2964
    Prev
    Next
    INDEX
    Explanations

    sales and learn

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

    bold formatting around section titles

    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
    JAM
    0.36
    包
    0.35
    TYPES
    0.34
    3
    0.34
    लेकिन
    0.34
    क
    0.33
    تو
    0.33
    隔离
    0.31
    د
    0.31
     R
    0.31
    POSITIVE LOGITS
    meng
    0.38
     heartwarming
    0.36
     pesky
    0.36
     had
    0.35
     merupakan
    0.35
    had
    0.35
     ಬಹಳ
    0.34
    been
    0.34
    lama
    0.34
     longstanding
    0.34
    Activations Density 0.203%

    No Known Activations