© 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. 218977
    Prev
    Next
    INDEX
    Explanations

    Republican aspirants

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

    breakdown and assessment

    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
    法语
    0.54
     忄
    0.50
     Halke
    0.48
     زمین
    0.46
     ฟ้า
    0.46
    髂
    0.46
    西哥
    0.45
    CGPoint
    0.45
    拁
    0.45
    르면
    0.45
    POSITIVE LOGITS
     murdered
    0.47
     the
    0.44
     slain
    0.43
     blasted
    0.42
     landlord
    0.41
     malignancy
    0.41
     democracies
    0.39
     murdering
    0.39
     chickens
    0.39
     bankrupt
    0.39
    Activations Density 0.000%

    No Known Activations