© 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. 34-GEMMASCOPE-RES-131K
    7. 92267
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

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

    This neuron detects programming identifiers—things like variable names, class names, method names, and other code‐specific tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    }>;
    -0.84
    raeli
    -0.82
     за
    -0.81
     gerekti
    -0.77
     x
    -0.77
    relle
    -0.76
     х
    -0.75
     game
    -0.75
    ogene
    -0.73
    rache
    -0.73
    POSITIVE LOGITS
    جویان
    0.97
     ↓,
    0.91
     téléchargement
    0.89
     imprimer
    0.88
     hive
    0.87
    umnos
    0.86
     continuant
    0.84
     PEDRO
    0.84
    itteet
    0.84
    licability
    0.83
    Activations Density 0.003%

    No Known Activations