© 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. 124762
    Prev
    Next
    INDEX
    Explanations

    G summits, FDA, attacks, Wed, industry, extended genealogy, completely covered, failure to

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

    Bug Fix, list documentation

    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
    ⚖
    0.50
     لے
    0.50
    лежа
    0.47
    UPI
    0.47
    дзе
    0.47
    PPI
    0.46
    ड़ा
    0.46
    FJ
    0.46
    realm
    0.46
    Rescue
    0.45
    POSITIVE LOGITS
     Fax
    0.55
    </h2>
    0.49
     étroite
    0.49
     Misc
    0.47
     Visions
    0.46
    訓
    0.46
     curs
    0.45
     Americas
    0.45
     Images
    0.45
     Midi
    0.44
    Activations Density 0.000%

    No Known Activations