© 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. 130144
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on numeric literals (standalone numbers) in code.

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

    `for i` loop

    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
     also
    -1.18
     that
    -1.09
    、《
    -0.95
     a
    -0.94
     anything
    -0.88
     jeden
    -0.88
    itizing
    -0.88
     aspetti
    -0.88
     späteren
    -0.87
     mainly
    -0.86
    POSITIVE LOGITS
     เล
    1.00
    poptosis
    1.00
    Lähde
    0.98
    の人に
    0.96
    licante
    0.96
     MÉXICO
    0.93
    争取
    0.93
    Katso
    0.92
    icidio
    0.91
    postolic
    0.90
    Activations Density 0.003%

    No Known Activations