© 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. 49705
    Prev
    Next
    INDEX
    Explanations

    technical documentation, code, and legal text

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

    This neuron detects numeric tokens or sequences of digits (i.e., numbers).

    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
    for
    -0.94
    For
    -0.91
     For
    -0.91
    ForAll
    -0.90
     Ten
    -0.80
     for
    -0.79
    FOR
    -0.70
    à
    -0.69
     ten
    -0.68
    為
    -0.67
    POSITIVE LOGITS
    Sean
    0.79
     Gone
    0.73
     accessoires
    0.72
     Sean
    0.72
     Racing
    0.69
     Streptococcus
    0.68
     Chré
    0.68
    Xing
    0.67
    пче
    0.66
    ἔ
    0.66
    Activations Density 0.644%

    No Known Activations