© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40270
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     in
    -1.83
     the
    -1.82
    ristor
    -1.70
    d
    -1.67
    n
    -1.66
    这是什么
    -1.59
    h
    -1.58
    brtc
    -1.56
     what
    -1.55
     lacking
    -1.55
    POSITIVE LOGITS
    .
    2.20
     PÅ
    1.88
    ichtete
    1.82
     Paroles
    1.69
     vedno
    1.66
    левая
    1.54
     clásica
    1.52
     Füße
    1.52
    abaikan
    1.50
    ٦
    1.50
    Activations Density 0.000%

    No Known Activations