© 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. 4112
    Prev
    Next
    INDEX
    Explanations

    metadata and disclaimers

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

    The neuron fires on numerical tokens (e.g., standalone numbers or version numbers) within the text.

    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
    的不
    -0.74
     TUT
    -0.74
    ђе
    -0.72
    Temperature
    -0.71
     sélectionnés
    -0.71
    колай
    -0.71
    ąb
    -0.70
    ographed
    -0.68
    ولت
    -0.67
    WindowEvent
    -0.66
    POSITIVE LOGITS
    ppert
    0.76
     UA
    0.68
     وهذا
    0.67
    чности
    0.66
    denial
    0.66
     Dancers
    0.62
     сты
    0.62
     Marker
    0.61
     advantageous
    0.61
    дента
    0.60
    Activations Density 0.056%

    No Known Activations