© 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. 64405
    Prev
    Next
    INDEX
    Explanations

    programming terms and news topics

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

    The neuron selectively fires on programming‐style identifiers and other domain‐specific “content” tokens (e.g. CamelCase/PascalCase names, code/API identifiers, key technical terms), rather than on ordinary stopwords or punctuation.

    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
    訖
    -0.81
     神社
    -0.81
    டன்
    -0.77
    れていた
    -0.76
    鯤
    -0.73
     phút
    -0.73
    Lew
    -0.72
     femur
    -0.72
    Cook
    -0.71
    Neg
    -0.70
    POSITIVE LOGITS
    FOTOS
    0.91
    Дру
    0.86
    Wür
    0.86
     pazi
    0.85
    /<
    0.85
    clonal
    0.84
    Gute
    0.82
     olhar
    0.79
     tornou
    0.78
    coroutine
    0.78
    Activations Density 0.004%

    No Known Activations