© 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. 181149
    Prev
    Next
    INDEX
    Explanations

    Bible Story

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

    Docker, subscriptions, help

    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
    iszt
    0.47
     upravo
    0.46
     parlé
    0.43
    🥞
    0.43
    পূর্ব
    0.42
    idamente
    0.42
    泊
    0.42
    बाजी
    0.42
     parla
    0.42
    畔
    0.42
    POSITIVE LOGITS
    ўцаў
    0.50
     sumptuous
    0.45
     subtleties
    0.45
     Kirchen
    0.43
     submits
    0.42
     extravagant
    0.42
     oaths
    0.42
     අය
    0.42
     footnotes
    0.41
    कियों
    0.41
    Activations Density 0.000%

    No Known Activations