© 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. 237727
    Prev
    Next
    INDEX
    Explanations

    events and announcements

    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
     needful
    0.52
     till
    0.48
    rs
    0.48
    KI
    0.47
    '$.
    0.47
     kudu
    0.46
     availed
    0.46
    $.
    0.45
     resorted
    0.45
     kabhi
    0.45
    POSITIVE LOGITS
    Dynamics
    0.48
    apen
    0.47
     издания
    0.46
    }>
    0.46
    ading
    0.46
    チャン
    0.46
    斻
    0.44
    䀠
    0.44
    塑造
    0.44
    臤
    0.44
    Activations Density 0.000%

    No Known Activations