© 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. 22-GEMMASCOPE-RES-131K
    7. 15510
    Prev
    Next
    INDEX
    Explanations

    code function signatures

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

    This neuron detects numeric literal tokens (e.g. integers) 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_22/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
     their
    -2.23
     even
    -1.88
     not
    -1.86
     first
    -1.82
     all
    -1.80
     two
    -1.79
     now
    -1.76
     more
    -1.74
     at
    -1.66
     individuals
    -1.66
    POSITIVE LOGITS
    튿
    1.82
     trám
    1.80
     ซึ่ง
    1.47
     militer
    1.44
     détaillés
    1.41
     เมื่อ
    1.41
    ⾒
    1.39
     CURRENT
    1.38
    Kilde
    1.38
     portavoz
    1.38
    Activations Density 0.017%

    No Known Activations