© 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. 52452
    Prev
    Next
    INDEX
    Explanations

    our identity, languages, locals

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

    generation, child, violence, calendar, compress

    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
     cars
    0.49
    ;
    0.47
     znacz
    0.47
     ขอ
    0.45
     większość
    0.45
     deaths
    0.45
     extin
    0.45
     comp
    0.44
     crimes
    0.44
     neuer
    0.44
    POSITIVE LOGITS
     Locally
    0.54
    㭚
    0.54
    َي
    0.50
    ુ
    0.49
    閭
    0.49
    ುಂಬ
    0.48
     Locals
    0.48
     Solve
    0.46
    感覺
    0.46
     Creates
    0.46
    Activations Density 0.000%

    No Known Activations