© 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. 15489
    Prev
    Next
    INDEX
    Explanations

    wir, we, or related names

    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
    饪
    -2.95
     sabid
    -2.69
     apolog
    -2.67
    🪤
    -2.64
    祧
    -2.61
    纡
    -2.59
    和其他
    -2.50
     frança
    -2.50
    谞
    -2.45
    髕
    -2.39
    POSITIVE LOGITS
    self
    2.92
    </i>
    2.55
     komplette
    2.38
     einzelne
    2.34
     この
    2.30
     なら
    2.28
     penchant
    2.27
    壜
    2.23
     offizielle
    2.23
     expri
    2.23
    Activations Density 0.000%

    No Known Activations