© 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. 68396
    Prev
    Next
    INDEX
    Explanations

    arctic and articulate

    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
    -2.98
    ㉖
    -2.58
     correta
    -2.39
    
    -2.25
     його
    -2.22
    氿
    -2.20
     放題
    -2.09
    鳧
    -2.08
    "¿
    -2.08
     midst
    -2.08
    POSITIVE LOGITS
    </b>
    2.58
     После
    2.48
     от
    2.47
    ↵
    2.45
     ?
    2.38
    一瞬
    2.31
     builds
    2.30
     embarrass
    2.25
    </code>
    2.23
     evident
    2.16
    Activations Density 0.145%

    No Known Activations