© 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. 7212
    Prev
    Next
    INDEX
    Explanations

    {{ curly brace }} or < tag >

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

    The neuron activates on standalone numeric literals (sequences of digits) in code or 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
    ↷
    -0.82
     sarees
    -0.81
    ยิ่ง
    -0.80
    可
    -0.80
     vpon
    -0.78
     venn
    -0.78
    いただける
    -0.78
    👀
    -0.78
     viking
    -0.78
    dite
    -0.78
    POSITIVE LOGITS
    //
    1.53
     //
    1.15
     edades
    0.95
     précieux
    0.93
    ;
    0.90
     promesas
    0.90
    documented
    0.90
    preventDefault
    0.89
     dude
    0.89
     daje
    0.88
    Activations Density 0.003%

    No Known Activations