© 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. 41733
    Prev
    Next
    INDEX
    Explanations

    historical context and beginnings

    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
    AN
    0.55
    ANT
    0.54
    IN
    0.53
    น
    0.53
    MIN
    0.53
     MUN
    0.52
    ING
    0.52
    ANA
    0.52
     Trojan
    0.50
    G
    0.50
    POSITIVE LOGITS
    şı
    0.48
     giấy
    0.45
    nimmt
    0.45
    getSize
    0.42
     época
    0.42
    ibfk
    0.42
     இதனால்
    0.41
    ším
    0.41
     వరకు
    0.41
    őbb
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.