© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69798
    Prev
    Next
    INDEX
    Explanations

    code and math punctuation

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

    The neuron is primarily detecting numeric literals (numbers, including integers and decimals) 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_10/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
     problèmes
    -1.95
     enorme
    -1.83
     appétit
    -1.81
    ã
    -1.77
     normales
    -1.75
     enormes
    -1.70
     avocat
    -1.68
     elegante
    -1.67
     presque
    -1.65
     magnifique
    -1.63
    POSITIVE LOGITS
     its
    2.33
     and
    2.14
     during
    2.09
     to
    2.08
     until
    2.06
     such
    2.03
     from
    2.00
     after
    1.98
     before
    1.90
     includes
    1.89
    Activations Density 0.062%

    No Known Activations