© 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. 71533
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat. No

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

    This neuron activates on individual numeric digits (i.e. numeral characters) in the text.

    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
     CÁ
    -0.90
    لسی
    -0.89
    kuchen
    -0.89
    gether
    -0.85
    losti
    -0.84
    栊
    -0.84
    мать
    -0.81
    Ꮣ
    -0.81
    ulir
    -0.81
    neden
    -0.80
    POSITIVE LOGITS
    此时的
    0.87
     terceiro
    0.87
    还有什么
    0.83
     sustained
    0.82
     Rip
    0.82
     zig
    0.80
     explicou
    0.79
    你自己
    0.78
     widać
    0.78
    与此
    0.77
    Activations Density 0.008%

    No Known Activations