© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 216162
    Prev
    Next
    INDEX
    Explanations

    large radius

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

    people, AI, novels, consequences, horses

    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
    Negative Logits
    leadsto
    0.45
     sonuç
    0.45
    markets
    0.44
     elasticity
    0.43
     specialist
    0.43
     malignancy
    0.43
     العليا
    0.43
     procent
    0.42
    t
    0.42
    tól
    0.42
    POSITIVE LOGITS
    apiRequest
    0.47
     Joe
    0.45
    하기
    0.45
     আবেগ
    0.45
     আবশ্যক
    0.44
    腿
    0.44
    व्हा
    0.44
     Carry
    0.44
     Jamie
    0.44
     Bear
    0.44
    Activations Density 0.001%

    No Known Activations