© 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. 34-GEMMASCOPE-RES-131K
    7. 93654
    Prev
    Next
    INDEX
    Explanations

    java package identifiers starting with org

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    íř
    -0.95
    Ꮹ
    -0.86
     Chinois
    -0.85
    bouncycastle
    -0.85
    
    -0.84
    HASAN
    -0.83
     ederim
    -0.81
     chanteuse
    -0.81
    /...
    -0.80
     previsão
    -0.80
    POSITIVE LOGITS
    example
    0.96
     Nhưng
    0.93
     requerido
    0.88
    utiny
    0.88
    iesis
    0.85
     no
    0.84
    yaç
    0.84
    χ
    0.84
    хів
    0.83
    你就
    0.83
    Activations Density 0.009%

    No Known Activations