© 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. 176255
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific entities

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

    seeking out

    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
    ibald
    0.42
     Liberties
    0.41
     Books
    0.40
     Freeman
    0.40
     һ
    0.40
     Freed
    0.40
     McLaughlin
    0.40
    books
    0.39
     Mead
    0.39
    Books
    0.39
    POSITIVE LOGITS
    リス
    0.50
    ूर
    0.48
     classico
    0.47
    으로
    0.45
     loser
    0.44
    น
    0.44
     classique
    0.44
    FAKE
    0.42
    зме
    0.42
    용한
    0.42
    Activations Density 0.001%

    No Known Activations