© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58661
    Prev
    Next
    INDEX
    Explanations

    free variables and fixed fields

    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
     framför
    -0.78
    vikling
    -0.77
    ウィキ
    -0.76
    LEE
    -0.74
     tights
    -0.74
    Instrucciones
    -0.71
    executor
    -0.69
    exec
    -0.69
    лио
    -0.69
     copo
    -0.68
    POSITIVE LOGITS
     constants
    1.05
     symbols
    0.96
     variables
    0.95
     Variable
    0.94
     constantes
    0.88
     Var
    0.88
     symbol
    0.88
     Constants
    0.86
    Variables
    0.85
     free
    0.85
    Activations Density 0.025%

    No Known Activations