© 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. 59981
    Prev
    Next
    INDEX
    Explanations

    Minnesota, Wisconsin places

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

    The neuron consistently lights up on numeric tokens—individual digits and multi‐digit numbers (years, scores, counts, route numbers, etc.)—regardless of context.

    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
    vertical
    -0.76
     Proben
    -0.75
    pright
    -0.75
     hå
    -0.72
     زد
    -0.72
     chalk
    -0.69
     LOCAL
    -0.69
    coccal
    -0.68
    includegraphics
    -0.68
    =$_
    -0.67
    POSITIVE LOGITS
     dode
    0.76
    нный
    0.76
     Stearns
    0.75
    འ
    0.73
    ADJUST
    0.73
     topo
    0.72
    CNS
    0.71
     Kaspersky
    0.71
     Berta
    0.70
    вети
    0.70
    Activations Density 0.013%

    No Known Activations