© 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. 10-GEMMASCOPE-RES-131K
    7. 9327
    Prev
    Next
    INDEX
    Explanations

    code and programming languages

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

    This neuron detects numeric literals (numbers) in code, regardless of language or context.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ↵↵
    -1.49
    вный
    -1.45
     largely
    -1.40
    -1.38
     shown
    -1.37
     poseen
    -1.36
     wegen
    -1.32
     Propiedad
    -1.30
     reciben
    -1.30
     a
    -1.29
    POSITIVE LOGITS
    فایل
    1.75
    Zusammenfassung
    1.60
    تحميل
    1.45
    ※※
    1.42
    зывают
    1.42
     These
    1.42
    Lähde
    1.39
     invigor
    1.38
    Dzień
    1.37
    こともある
    1.34
    Activations Density 0.013%
    No Known Activations