© 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. 116342
    Prev
    Next
    INDEX
    Explanations

    license text and code identifiers

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

    The neuron is detecting numeric tokens (numbers, dates, prices, or other digit sequences).

    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
    verband
    -0.78
    modules
    -0.73
     Bakterien
    -0.72
    全局
    -0.72
     využ
    -0.69
    gien
    -0.69
     владель
    -0.68
     použití
    -0.68
    ASY
    -0.68
    生效
    -0.68
    POSITIVE LOGITS
     procédure
    0.71
    basedir
    0.69
    adays
    0.68
    Chandigarh
    0.68
     Landon
    0.67
    owska
    0.66
    xmlWriter
    0.63
    François
    0.61
    ensores
    0.60
    ื
    0.60
    Activations Density 0.063%

    No Known Activations