© 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. 34-GEMMASCOPE-RES-131K
    7. 90973
    Prev
    Next
    INDEX
    Explanations

    configuration properties and settings

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

    The neuron is specialized in spotting numeric literal tokens (e.g. integer or floating-point constants) in source‐code or data.

    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
    тию
    -0.82
    ্ট
    -0.81
    ahren
    -0.79
    teclado
    -0.76
    BackPressed
    -0.73
    жется
    -0.73
    deinit
    -0.73
    Sculpture
    -0.71
     emlé
    -0.70
     libc
    -0.69
    POSITIVE LOGITS
     flags
    0.96
     materials
    0.90
     material
    0.88
     scale
    0.87
     colors
    0.87
    譯
    0.86
    bill
    0.85
    materials
    0.84
     brightness
    0.84
     LOD
    0.84
    Activations Density 0.027%

    No Known Activations