© 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. 22-GEMMASCOPE-RES-131K
    7. 84031
    Prev
    Next
    INDEX
    Explanations

    status codes and error messages

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

    The neuron fires on identifiers of external libraries or modules in import/using statements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Utilisez
    -0.90
    oraus
    -0.89
     pretože
    -0.88
     cechy
    -0.87
    htbp
    -0.87
     közül
    -0.85
     Whether
    -0.85
     rho
    -0.85
    phs
    -0.84
     Descripción
    -0.84
    POSITIVE LOGITS
    ктория
    0.95
    ("")
    0.89
    礎
    0.88
    wór
    0.87
     lover
    0.85
    ？」
    0.81
    HttpStatus
    0.81
     gang
    0.80
     commit
    0.79
    傘
    0.79
    Activations Density 0.003%

    No Known Activations