© 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. 124006
    Prev
    Next
    INDEX
    Explanations

    price or date

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

    Spanish and Chinese words

    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
    eraient
    0.45
    otherm
    0.44
    NASDAQ
    0.44
    ◜
    0.44
     निगरानी
    0.44
    citing
    0.44
     おすすめ
    0.44
    uffix
    0.43
     പഠ
    0.42
    ルド
    0.42
    POSITIVE LOGITS
     calmly
    0.44
     situación
    0.43
     repressive
    0.43
     violación
    0.42
     región
    0.42
     intérpre
    0.41
     possible
    0.40
    $).
    0.40
     حملہ
    0.40
    gação
    0.39
    Activations Density 0.001%

    No Known Activations