© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21003
    Prev
    Next
    INDEX
    Explanations

    center of domain or activity

    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
     ersche
    -1.62
     største
    -1.57
     voegen
    -1.55
     serce
    -1.55
    </i>
    -1.55
     всички
    -1.53
     resultaat
    -1.50
    absorbing
    -1.50
    ⽇
    -1.49
    しましたが
    -1.48
    POSITIVE LOGITS
    c
    1.90
    k
    1.70
    s
    1.66
    </sup>
    1.58
    to
    1.56
    
    1.54
    in
    1.51
    Ꮉ
    1.48
    鈊
    1.45
    le
    1.45
    Activations Density 0.039%

    No Known Activations