© 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. 10052
    Prev
    Next
    INDEX
    Explanations

    Key terms following formatting

    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
    BySize
    0.44
    ক্কা
    0.44
    лектро
    0.41
    timeLeft
    0.40
    嬰
    0.40
    міна
    0.40
    сія
    0.39
     drawSprites
    0.39
     ساي
    0.39
    जब
    0.39
    POSITIVE LOGITS
     Council
    0.41
     Ministry
    0.40
     Guid
    0.40
     Councils
    0.38
     Ru
    0.37
     별
    0.37
     County
    0.36
     Frenchman
    0.36
     Commissioner
    0.35
     City
    0.35
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.