© 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. 99511
    Prev
    Next
    INDEX
    Explanations

    ribbon cutting ceremony

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

    content warning

    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
     liquidated
    0.47
     unoccupied
    0.46
     vacuoles
    0.45
     ECO
    0.44
    獷
    0.43
     ionized
    0.43
     enduro
    0.43
     hydrazine
    0.42
     teak
    0.42
     carpentry
    0.41
    POSITIVE LOGITS
    Bankr
    0.48
    Coref
    0.48
    WriteHeader
    0.48
     অন্তর্
    0.48
     Einstellung
    0.47
    <0x0D>
    0.46
     mirada
    0.46
    ai
    0.46
     Verständ
    0.46
    ழுகு
    0.46
    Activations Density 0.003%

    No Known Activations