© 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. 90851
    Prev
    Next
    INDEX
    Explanations

    academic or code metadata

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

    The neuron chiefly responds to numeric tokens—i.e. occurrences of numbers or digit sequences in the text.

    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
     Organizer
    -0.72
     ene
    -0.72
    ภา
    -0.71
     rz
    -0.71
     Mahan
    -0.70
    reth
    -0.69
     FLAC
    -0.68
    轻松
    -0.68
     noten
    -0.67
     negócio
    -0.67
    POSITIVE LOGITS
     systemic
    0.95
     system
    0.93
     систем
    0.87
    System
    0.84
     SYSTEM
    0.79
     sistem
    0.78
    Sys
    0.77
     System
    0.75
     getSystem
    0.74
     Systemic
    0.73
    Activations Density 0.035%

    No Known Activations