© 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. 60493
    Prev
    Next
    INDEX
    Explanations

    fractions and measurements

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

    This neuron fires on numeric measurements—especially fractions and decimal numbers (e.g. “1/2,” “12.875,” “44.5”).

    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
     it
    -1.86
     has
    -1.69
    9
    -1.63
     new
    -1.60
     there
    -1.59
    ;
    -1.59
    -1.54
    _
    -1.49
     used
    -1.45
    ’
    -1.45
    POSITIVE LOGITS
    /")
    1.76
    だったので
    1.73
     jambes
    1.53
    managers
    1.51
     verschillende
    1.49
    siti
    1.48
     ไม่
    1.47
    妡
    1.43
     automóviles
    1.40
    nexpected
    1.39
    Activations Density 0.006%
    No Known Activations