© 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. 20883
    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
    tellungen
    -0.99
    datable
    -0.97
    UC
    -0.97
     ICP
    -0.94
    asties
    -0.93
    沙发
    -0.90
    ꪔ
    -0.90
     финансо
    -0.90
    itisation
    -0.88
    ̓
    -0.87
    POSITIVE LOGITS
     lẫn
    0.96
     到着
    0.90
     khoản
    0.90
    Kanye
    0.90
    maxWidth
    0.89
    Nath
    0.88
     jahre
    0.87
     maxWidth
    0.85
     gewesen
    0.84
     manquer
    0.83
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.