© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 23717
    Prev
    Next
    INDEX
    Explanations

    Stone flaming

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

    The neuron strongly activates on numeric tokens—sequences of digits like version numbers, years, IDs, and similar 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
     Throttle
    -0.77
     مشتری
    -0.77
     bầu
    -0.76
     bunu
    -0.75
    iky
    -0.75
    enovo
    -0.74
    orno
    -0.74
    жем
    -0.73
     comedies
    -0.71
     Item
    -0.71
    POSITIVE LOGITS
    minar
    0.78
    '>{
    0.77
    postal
    0.75
    Dancer
    0.74
     plá
    0.72
    derry
    0.71
     skit
    0.70
    мба
    0.70
     plataformas
    0.69
    getc
    0.68
    Activations Density 0.015%

    No Known Activations