© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22185
    Prev
    Next
    INDEX
    Explanations

    泛 type

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

    The neuron fires on standalone numeric tokens (digits-only), i.e. it detects numbers in code and comments.

    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
    carian
    -1.99
     hlavy
    -1.72
     Feuchtigkeit
    -1.66
     Erkennt
    -1.60
     who
    -1.60
     Vernunft
    -1.60
     pedras
    -1.59
     vandens
    -1.59
     »
    -1.55
     Weisheit
    -1.52
    POSITIVE LOGITS
     istan
    2.22
     {
    2.00
     kedai
    1.95
     bensin
    1.95
     passat
    1.94
     Rossa
    1.91
     pasaran
    1.89
     gula
    1.88
     krim
    1.87
     sentra
    1.87
    Activations Density 0.014%

    No Known Activations