© 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. 10-GEMMASCOPE-RES-131K
    7. 103728
    Prev
    Next
    INDEX
    Explanations

    numbers following specific tokens

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

    This neuron activates on numeric labels and codes—e.g. docket numbers, section or volume citations, figure/year identifiers, and other digit-based markers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    4
    -1.55
     or
    -1.50
     and
    -1.35
    RUnlock
    -1.32
     there
    -1.31
    There
    -1.31
    sidian
    -1.31
    「
    -1.31
     AWESOME
    -1.30
     والأ
    -1.29
    POSITIVE LOGITS
     reação
    1.64
     anhänger
    1.63
     tromper
    1.56
     нашим
    1.52
     iklan
    1.50
     ligação
    1.47
     redução
    1.46
     our
    1.45
     paixão
    1.38
     opção
    1.38
    Activations Density 0.024%

    No Known Activations