© 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. 70103
    Prev
    Next
    INDEX
    Explanations

    code syntax

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

    The neuron fires on numeric literals (integers or floats) in code.

    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
    These
    -1.85
    0
    -1.80
    for
    -1.75
    We
    -1.73
    This
    -1.70
    For
    -1.67
    Every
    -1.67
    7
    -1.66
     anderer
    -1.63
     deinen
    -1.63
    POSITIVE LOGITS
     a
    2.17
     continúas
    1.74
    εται
    1.55
    чении
    1.48
     about
    1.45
     its
    1.45
     herhangi
    1.43
    <!--
    1.41
     in
    1.41
    vieve
    1.41
    Activations Density 0.006%

    No Known Activations