© 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. 236318
    Prev
    Next
    INDEX
    Explanations

    definitions, specific terms, or states

    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
     секрета
    0.47
     คูณ
    0.44
     актив
    0.43
     мероприятий
    0.42
    queous
    0.42
     Consume
    0.42
    斧
    0.42
     Ад
    0.42
     чай
    0.42
     підприєм
    0.42
    POSITIVE LOGITS
    ang
    0.50
    Coins
    0.47
    ुभ
    0.47
    coins
    0.45
     सितारों
    0.45
    𝗵
    0.45
    Format
    0.45
    φ
    0.44
    キ
    0.44
    errors
    0.44
    Activations Density 0.000%

    No Known Activations