© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 73484
    Prev
    Next
    INDEX
    Explanations

    historical narratives and facts

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

    tokens

    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
    仅
    0.46
    Amin
    0.45
    мы
    0.43
    U
    0.43
    增速
    0.43
    Џ
    0.43
     Amin
    0.43
    е
    0.43
    ка
    0.42
    pannt
    0.42
    POSITIVE LOGITS
     HISTORY
    0.49
    วัติ
    0.45
     definiciones
    0.45
     létre
    0.45
    ल्टा
    0.44
     honours
    0.44
     mT
    0.44
     historia
    0.43
     SPIR
    0.43
     ancestor
    0.43
    Activations Density 0.003%

    No Known Activations