© 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. 99411
    Prev
    Next
    INDEX
    Explanations

    URLs and code snippets

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

    The neuron activates on tokens containing digits, effectively detecting numeric strings (e.g. version numbers, years, IDs).

    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
     مث
    -0.82
     παρα
    -0.79
     Blacks
    -0.76
    аза
    -0.75
    hashMap
    -0.73
     }}$.
    -0.73
    級
    -0.73
    currentIndex
    -0.72
    点は
    -0.72
    вель
    -0.72
    POSITIVE LOGITS
     ope
    0.81
    場合には
    0.79
     cresce
    0.77
    ほんと
    0.77
    addressed
    0.76
    outlined
    0.76
     denounced
    0.75
     Distinct
    0.75
     dense
    0.75
    NOTAS
    0.75
    Activations Density 0.737%

    No Known Activations