© 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. 71792
    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
     хотят
    -1.05
    Ꮞ
    -1.02
    Цели
    -0.97
     habeas
    -0.96
    우스
    -0.96
     rámci
    -0.95
    czema
    -0.94
    alui
    -0.94
     проєкту
    -0.93
    Хочу
    -0.93
    POSITIVE LOGITS
     Decke
    1.10
    |'
    1.05
     nebo
    1.02
    crazy
    1.00
     collega
    0.99
     corriente
    0.98
     trady
    0.97
     том
    0.92
     ή
    0.92
    corporated
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.