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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 119028
    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
     ERK
    -0.99
    薬品
    -0.96
     {#
    -0.92
    西兰
    -0.92
     repertoire
    -0.92
    -0.91
    ⩾
    -0.89
    uhr
    -0.89
    IOM
    -0.87
    ≃
    -0.87
    POSITIVE LOGITS
    </em>
    0.93
     dikel
    0.90
     Needless
    0.87
     superiore
    0.87
     or
    0.86
    目的是
    0.86
    rali
    0.85
     hark
    0.85
    ISSION
    0.84
    ских
    0.84
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.