© 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. 34-GEMMASCOPE-RES-131K
    7. 70188
    Prev
    Next
    INDEX
    Explanations

    Am, wk, Mass

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

    The neuron responds to numeric tokens (digits and numbers) 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_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
     while
    -1.03
     mientras
    -0.77
    девушка
    -0.76
    ficiencia
    -0.76
    ieden
    -0.75
     Sah
    -0.75
     WeChat
    -0.75
    iffs
    -0.73
    тивен
    -0.71
    primitive
    -0.71
    POSITIVE LOGITS
    Oxygen
    0.79
     lapsed
    0.72
    ༓
    0.71
    nul
    0.70
     الساعة
    0.69
     speechless
    0.69
    有名な
    0.69
     tố
    0.69
    〡
    0.69
    łania
    0.69
    Activations Density 0.018%

    No Known Activations