© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32603
    Prev
    Next
    INDEX
    Explanations

    code syntax and definitions

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

    This neuron fires on numeric literals (sequences of digits or numbers) in the text.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     verres
    -0.90
    雖然
    -0.88
     برای
    -0.88
     malha
    -0.88
     또
    -0.85
    Ży
    -0.85
    ्ञ
    -0.84
    𝙠
    -0.84
     amorti
    -0.84
    Δια
    -0.83
    POSITIVE LOGITS
     one
    1.00
    ねて
    0.90
     heights
    0.83
     tendencies
    0.83
    getNew
    0.82
     see
    0.81
     than
    0.80
    娛
    0.80
     collections
    0.78
    hances
    0.78
    Activations Density 0.049%

    No Known Activations