© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57278
    Prev
    Next
    INDEX
    Explanations

    classifying data into groups

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

    This neuron detects programming/code segments (e.g. function names, code keywords, punctuation, and numeric literals).

    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
    jetbrains
    -0.86
     lembrar
    -0.82
     porcentaje
    -0.80
    年は
    -0.79
     douleurs
    -0.75
    ⠏
    -0.75
     Percentage
    -0.75
    läng
    -0.75
     sợi
    -0.74
    ån
    -0.73
    POSITIVE LOGITS
     categories
    2.58
     classes
    2.17
     category
    2.13
     groups
    1.98
     bins
    1.89
     class
    1.85
    categories
    1.82
     intervals
    1.77
    Categories
    1.77
     Categories
    1.72
    Activations Density 0.121%

    No Known Activations