© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58288
    Prev
    Next
    INDEX
    Explanations

    seen or unseen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     to
    -2.70
    ”
    -2.28
    </u>
    -2.25
    </h1>
    -2.13
    ";
    -1.99
    觔
    -1.95
     \
    -1.92
     he
    -1.87
    “
    -1.81
    k
    -1.80
    POSITIVE LOGITS
    '
    3.13
    "
    2.45
    閦
    2.19
    寕
    2.17
    떳
    2.05
    ⑊
    2.00
    ਗ਼
    1.96
    いろいろ
    1.95
    他们的
    1.95
     alberga
    1.92
    Activations Density 0.011%

    No Known Activations