© 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. 181351
    Prev
    Next
    INDEX
    Explanations

    allows students, bring proper, meta data, imagine riding

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

    ignited public

    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
    Chain
    0.55
    X
    0.54
    ین
    0.51
    W
    0.50
    Asc
    0.49
    Capture
    0.48
     खांसी
    0.48
    適
    0.47
    фі
    0.46
    chained
    0.46
    POSITIVE LOGITS
     Bož
    0.49
    áles
    0.48
    wj
    0.47
     洋
    0.46
    ıc
    0.44
     jie
    0.44
     관한
    0.44
    兖
    0.44
     pj
    0.42
     diskusi
    0.42
    Activations Density 0.000%

    No Known Activations