© 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. 119154
    Prev
    Next
    INDEX
    Explanations

    col-md-, CV, cr

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

    The neuron strongly activates on numeric tokens (digits), i.e. it detects 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
    produzione
    -1.04
    bbling
    -1.02
     With
    -1.02
    の地
    -1.00
    ignment
    -0.99
    Fifty
    -0.98
    tionally
    -0.95
     that
    -0.95
     sufficient
    -0.94
     what
    -0.94
    POSITIVE LOGITS
    がありますが
    1.17
     Colegio
    1.03
    などは
    1.03
     lokale
    1.02
    Introdução
    0.99
    col
    0.97
     absolut
    0.93
     quelle
    0.93
     descobrir
    0.91
     numai
    0.90
    Activations Density 0.002%

    No Known Activations