© 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. 12000
    Prev
    Next
    INDEX
    Explanations

    county, chain, vertical, public

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

    The neuron fires on numeric tokens (digits, version numbers, and other 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
    styles
    -0.77
    ladas
    -0.73
    ḟ
    -0.68
     instruction
    -0.67
     uważ
    -0.66
    properties
    -0.66
     Committee
    -0.66
    Committee
    -0.65
    leck
    -0.64
    
    -0.64
    POSITIVE LOGITS
    uetas
    0.78
    gum
    0.64
    혁
    0.64
    Mismatch
    0.61
     Amendments
    0.60
    HRT
    0.60
    彰
    0.60
    墨
    0.60
     anthropologists
    0.59
    Proc
    0.59
    Activations Density 0.098%

    No Known Activations