© 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. 105338
    Prev
    Next
    INDEX
    Explanations

    animation and ui layout

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

    The neuron fires on numeric literals—digits, numbers, and numeric constants embedded 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_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
    ּוֹ
    -2.13
    ֶּ
    -1.70
    ַּ
    -1.61
     these
    -1.57
    ִּ
    -1.49
     if
    -1.47
     intelligente
    -1.28
     этих
    -1.26
     fatale
    -1.26
     permanent
    -1.25
    POSITIVE LOGITS
     ܐ
    1.62
    MathML
    1.59
    ýchod
    1.57
    ׇ
    1.56
     allerede
    1.55
     tilbake
    1.55
     seguintes
    1.52
     skupina
    1.51
     incluso
    1.48
    órica
    1.48
    Activations Density 0.078%

    No Known Activations