© 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. 2923
    Prev
    Next
    INDEX
    Explanations

    comprise/rating/allow/program/provides/along/great/leader/Intake

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

    sequence starters

    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
    Depois
    0.54
    ಿಸ್ಟ
    0.52
    asel
    0.51
    НЕ
    0.51
     problemler
    0.50
    淔
    0.50
     restaurantes
    0.50
    Surely
    0.50
     cherish
    0.50
    Funcion
    0.49
    POSITIVE LOGITS
     Class
    0.52
     Midtown
    0.51
     Broad
    0.50
     Seven
    0.50
     SDK
    0.50
     Audience
    0.49
    jc
    0.49
     >
    0.48
     รา
    0.48
    ścic
    0.48
    Activations Density 0.000%

    No Known Activations