© 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. 73611
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    The neuron detects numeric tokens (individual digits and simple arithmetic symbols) in mathematical or numeric contexts.

    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
     ondes
    -0.82
     actually
    -0.78
    arten
    -0.74
    Откры
    -0.73
    弩
    -0.72
    ursor
    -0.72
     runny
    -0.71
    Actually
    -0.70
     such
    -0.69
    \|\
    -0.69
    POSITIVE LOGITS
    әм
    0.83
    hasMore
    0.79
    SpringBoot
    0.77
     месте
    0.77
     ciclos
    0.73
    Equi
    0.73
     Mold
    0.73
    瓯
    0.73
     могло
    0.71
    처
    0.71
    Activations Density 0.036%

    No Known Activations