© 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. 130207
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on numeric literals and constant values (numbers) in code.

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

    programming keywords

    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
    与此同时
    -1.05
    ctable
    -1.02
     who
    -0.99
    angelog
    -0.95
     know
    -0.94
    xff
    -0.94
    iri
    -0.93
    haviours
    -0.93
     recent
    -0.92
     StringTokenizer
    -0.91
    POSITIVE LOGITS
     ს
    1.00
     Уи
    0.95
    Baik
    0.94
     ASTM
    0.94
     замести
    0.91
    Türkiye
    0.89
    NgModule
    0.87
    Bie
    0.86
    bede
    0.85
    кладка
    0.85
    Activations Density 0.010%

    No Known Activations