© 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. 54035
    Prev
    Next
    INDEX
    Explanations

    case titles

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

    The neuron fires on long runs of whitespace or blank‐space formatting tokens (e.g. big indentations or separators).

    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
     occidentale
    -0.82
    GRAPHICAL
    -0.82
    摄像头
    -0.78
     American
    -0.78
     Isn
    -0.77
     perguntou
    -0.77
    atron
    -0.77
     Comes
    -0.77
    ：“……”
    -0.76
    exercises
    -0.76
    POSITIVE LOGITS
    ساز
    0.93
     отвер
    0.92
    ској
    0.91
    机遇
    0.87
     roca
    0.87
     irony
    0.87
    beitung
    0.86
    点が
    0.86
     Keny
    0.85
    jazdu
    0.85
    Activations Density 0.063%

    No Known Activations