© 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. 22-GEMMASCOPE-RES-131K
    7. 67241
    Prev
    Next
    INDEX
    Explanations

    numbers and interface descriptions

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

    This neuron fires on tokens that occur alongside or immediately before numeric labels or counts in technical/mathematical text—i.e. things like equation/section references, numbered items, and other tokens tied to explicit 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_22/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
     photos
    -0.96
     Dlatego
    -0.92
    pDialog
    -0.87
    urnum
    -0.86
    ഛ
    -0.85
     码
    -0.82
     Erhaltung
    -0.81
     Wortes
    -0.80
    zkiem
    -0.80
     jerseys
    -0.79
    POSITIVE LOGITS
     државе
    1.07
     цвят
    0.92
     отзыв
    0.92
    ⑩
    0.90
     tycker
    0.89
     impresora
    0.88
     ‘‘
    0.88
    ["_
    0.87
    ٺ
    0.86
     tiras
    0.85
    Activations Density 0.080%

    No Known Activations