© 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. 210178
    Prev
    Next
    INDEX
    Explanations

    foreign language names

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

    technical analysis and programming concepts

    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
    \"
    0.51
    حي
    0.48
    یک
    0.48
     Garbage
    0.46
    谒
    0.46
    https
    0.46
     Сергея
    0.46
    W
    0.46
    сти
    0.45
    <h2>
    0.44
    POSITIVE LOGITS
     hjälp
    0.48
     അയാൾ
    0.48
     bille
    0.47
     Kampf
    0.47
     skriv
    0.47
     Hilfe
    0.46
     dole
    0.46
     باس
    0.46
     ಆಧ
    0.46
     ഇപ്പോൾ
    0.46
    Activations Density 0.001%

    No Known Activations