© 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. 80229
    Prev
    Next
    INDEX
    Explanations

    He had, He never, comic on, care as

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

    potential consequences discussed

    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
    State
    0.48
     inzwischen
    0.48
    irt
    0.47
    Western
    0.46
     Policía
    0.46
    Conditional
    0.46
    Independence
    0.46
    o
    0.45
    Opposition
    0.44
    Election
    0.44
    POSITIVE LOGITS
     crawler
    0.52
     from
    0.50
     garages
    0.50
    耙
    0.50
     kred
    0.47
     on
    0.47
     punctures
    0.46
     pula
    0.46
     moving
    0.46
     whenever
    0.46
    Activations Density 0.002%

    No Known Activations