© 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. 117042
    Prev
    Next
    INDEX
    Explanations

    code and programming language constructs

    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
    enderal
    -0.81
    CURS
    -0.78
     convento
    -0.73
    迸
    -0.71
    peter
    -0.71
    二次
    -0.71
    はその
    -0.71
    ┉
    -0.70
     those
    -0.69
    тся
    -0.69
    POSITIVE LOGITS
     value
    0.94
     Value
    0.90
    Karol
    0.86
    Sö
    0.84
    Напомним
    0.84
    ToString
    0.82
    値
    0.82
    Hacer
    0.82
    
    0.82
     값
    0.80
    Activations Density 0.000%

    No Known Activations