© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13499
    Prev
    Next
    INDEX
    Explanations

    code and markup punctuation

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

    This neuron detects numeric literals 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
     by
    -1.35
     if
    -1.16
     even
    -1.14
    нија
    -1.02
     this
    -1.02
    Даже
    -1.01
     its
    -1.00
     from
    -0.98
     it
    -0.97
    tyw
    -0.97
    POSITIVE LOGITS
     begrenzt
    1.14
    osten
    1.13
     weitgehend
    1.12
    ↵↵↵↵↵↵↵↵↵↵↵↵
    1.09
    ())){
    1.05
     princí
    1.04
     şun
    1.04
     zincir
    1.04
    <blockquote>
    1.01
     tých
    1.00
    Activations Density 0.003%

    No Known Activations