© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101907
    Prev
    Next
    INDEX
    Explanations

    Java class and interface declaration

    np_acts-logits-general · gemini-2.5-flash-lite

    angle brackets in programming code, particularly for generic type declarations and templates.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    ‘
    -1.97
    >
    -1.95
    푣
    -1.86
    *
    -1.79
    m
    -1.79
     Sloveniji
    -1.69
    1
    -1.68
    
    -1.66
    -!
    -1.65
    _
    -1.65
    POSITIVE LOGITS
     professione
    2.30
    Enfant
    1.94
    
    1.81
     pouvoirs
    1.80
    狃
    1.79
     escuchadas
    1.77
     manoeuvre
    1.77
     impone
    1.72
     qualifié
    1.72
     appunt
    1.71
    Activations Density 0.004%

    No Known Activations