© 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. 14914
    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
    self
    -1.02
    支払い
    -0.96
    ↵
    -0.96
    ᾳ
    -0.91
     lados
    -0.90
    膻
    -0.90
    さの
    -0.90
     differed
    -0.88
     dotyczą
    -0.86
    impresa
    -0.85
    POSITIVE LOGITS
     sempre
    1.05
     nhiều
    0.99
    гряз
    0.93
    şem
    0.93
     请
    0.93
    Bitte
    0.91
     gratuites
    0.91
    essive
    0.90
     Okan
    0.90
    говой
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.