© 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. 84640
    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
    少しずつ
    -0.98
     THROUGH
    -0.95
     hordes
    -0.94
    ⡰
    -0.93
     tecnologias
    -0.93
     đến
    -0.93
     similar
    -0.91
     jusqu
    -0.87
     pingente
    -0.87
     sorriso
    -0.86
    POSITIVE LOGITS
    　　　
    1.06
    raktion
    1.03
    '/>
    1.03
    ⬅
    0.96
    ⤵
    0.93
    nict
    0.92
    UnitTesting
    0.92
    🔞
    0.91
     ANNEX
    0.90
     羅
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.