© 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. 213379
    Prev
    Next
    INDEX
    Explanations

    independent female

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

    Push, exodus, thorough methods

    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
    handler
    0.45
     Mechanism
    0.45
    Mechanism
    0.44
    ↵↵
    0.42
     mechanism
    0.42
    ;
    0.41
     digelar
    0.41
     Infrastructure
    0.40
     rehabilitated
    0.40
     Religious
    0.40
    POSITIVE LOGITS
     еле
    0.60
    馄
    0.54
     тексту
    0.52
    和大
    0.51
    itäten
    0.51
    ्यालय
    0.50
     склад
    0.50
     дві
    0.50
     và
    0.50
     дуже
    0.49
    Activations Density 0.001%

    No Known Activations