© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 47953
    Prev
    Next
    INDEX
    Explanations

    JavaScript UI frameworks

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

    The neuron strongly activates on numeric tokens (digits or digit sequences) such as version numbers, build numbers, or standalone numbers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Descubre
    -0.92
     tenisky
    -0.75
    middlewares
    -0.73
    Compatibility
    -0.73
     Français
    -0.72
    lowercase
    -0.72
    mgp
    -0.70
    presidente
    -0.69
     Existen
    -0.69
    Manipulation
    -0.69
    POSITIVE LOGITS
     aria
    0.89
    sima
    0.88
    aria
    0.82
     роли
    0.81
    ARIA
    0.77
     hg
    0.75
    там
    0.73
    owaniu
    0.73
    digheden
    0.73
    Dom
    0.73
    Activations Density 0.015%

    No Known Activations