© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21485
    Prev
    Next
    INDEX
    Explanations

    programmatic identifiers and names

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

    The neuron selectively activates on numeric literals (tokens containing digits, including integers and 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
     BOTH
    -1.52
    Ꮉ
    -1.34
     guerras
    -1.33
    psfrag
    -1.30
     ordinarily
    -1.28
    biendo
    -1.28
    quisar
    -1.27
    geox
    -1.27
    ágeno
    -1.27
     Если
    -1.27
    POSITIVE LOGITS
     who
    1.66
    in
    1.63
    any
    1.58
    to
    1.49
    matrix
    1.47
    >
    1.46
    array
    1.41
    1.41
     
    1.41
    print
    1.40
    Activations Density 0.004%
    No Known Activations