© 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. 22-GEMMASCOPE-RES-131K
    7. 130534
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric literals (especially numbers in code or JSON string form).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    JSON string values

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     it
    -1.73
     with
    -1.50
     during
    -1.46
     if
    -1.41
     Since
    -1.28
     while
    -1.24
     During
    -1.23
     at
    -1.22
     There
    -1.22
     all
    -1.20
    POSITIVE LOGITS
     appréci
    1.64
    ౦
    1.45
     emporter
    1.41
    ཿ
    1.41
     rám
    1.41
     ajouter
    1.41
     ouvrir
    1.41
     écouter
    1.37
     empêcher
    1.32
     détruire
    1.30
    Activations Density 0.043%

    No Known Activations