© 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. 73770
    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
    losen
    -1.00
    ać
    -0.99
    withCredentials
    -0.97
    ﹎
    -0.95
    колеп
    -0.94
    nú
    -0.93
    monial
    -0.93
     metrów
    -0.93
     lép
    -0.93
    ⟝
    -0.92
    POSITIVE LOGITS
    BeginInit
    1.02
     Gedanke
    0.91
    することができます
    0.90
    ごめんなさい
    0.89
    mathrm
    0.88
    妻
    0.87
    最后的
    0.84
     subver
    0.84
     Amerikaanse
    0.83
    小孩子
    0.83
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.