© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103876
    Prev
    Next
    INDEX
    Explanations

    lost if, License

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

    The neuron activates on multi‐digit numeric tokens (i.e. literal numbers) in code or comment 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
    郞
    -0.73
     hendak
    -0.71
     ')[
    -0.70
     Booth
    -0.69
     Ib
    -0.67
     booths
    -0.67
    ocardio
    -0.65
     العنوان
    -0.64
    sns
    -0.64
     Portsmouth
    -0.64
    POSITIVE LOGITS
     tron
    0.68
    ẑ
    0.68
    tagez
    0.68
     hap
    0.66
    morrow
    0.66
     fala
    0.65
    gemene
    0.65
    sterna
    0.65
    𝕙
    0.64
     tabac
    0.63
    Activations Density 0.106%

    No Known Activations