© 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. 12245
    Prev
    Next
    INDEX
    Explanations

    react imports

    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
    and
    0.56
    reform
    0.51
    ementerian
    0.46
    🦇
    0.46
    on
    0.45
    op
    0.45
    ها
    0.45
    mazing
    0.44
    terror
    0.44
    fn
    0.43
    POSITIVE LOGITS
     الخلق
    0.54
     το
    0.50
    賏
    0.50
     кожен
    0.47
    大致
    0.46
     الرئيسية
    0.46
     φ
    0.46
     Ρ
    0.45
     Το
    0.45
    Header
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.