© 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. 36597
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and code constructs

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

    The neuron fires on numeric tokens—i.e. integer literals and related numeric comparisons.

    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
    льный
    -1.13
    éducation
    -0.99
    ביוגרפיה
    -0.93
    Nationale
    -0.92
    asyarakat
    -0.91
    Groet
    -0.91
     ήταν
    -0.90
     puits
    -0.89
    Política
    -0.89
     Président
    -0.89
    POSITIVE LOGITS
    Q
    1.13
    Her
    1.09
    No
    1.06
    A
    1.03
    门的
    1.02
    を
    1.00
    The
    1.00
    In
    0.98
    P
    0.98
    He
    0.97
    Activations Density 0.006%

    No Known Activations