© 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. 59071
    Prev
    Next
    INDEX
    Explanations

    nine

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

    The neuron activates on tokens that are numeric or contain digits (e.g. counts, version numbers, IDs, years, sizes).

    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
     Juan
    -0.81
    ById
    -0.77
    Juan
    -0.72
    跎
    -0.71
    <0xE5>
    -0.71
    8
    -0.71
    Gary
    -0.69
    Ongoing
    -0.68
     Cambrian
    -0.68
    Billy
    -0.67
    POSITIVE LOGITS
     NINE
    0.87
     nine
    0.85
    9
    0.84
     nineteen
    0.83
     PyObject
    0.77
    جستارهای
    0.75
    <0xA1>
    0.75
    QString
    0.74
     Impression
    0.74
     Nineteen
    0.73
    Activations Density 1.527%

    No Known Activations