© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13952
    Prev
    Next
    INDEX
    Explanations

    reports findings or results

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

    The neuron is triggered by numbers and numeric data (e.g. measurements, quantities, figure or table references).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    (!__
    -1.23
    aneity
    -1.20
    leness
    -1.20
    ֻ
    -1.16
     this
    -1.16
     confortável
    -1.16
     a
    -1.16
     which
    -1.11
    alties
    -1.10
    ológicos
    -1.09
    POSITIVE LOGITS
     of
    1.45
     in
    1.44
     by
    1.34
     женская
    1.13
     мужская
    1.09
    in
    1.07
    ps
    1.00
     considération
    1.00
    軀
    0.99
    的精神
    0.99
    Activations Density 0.035%

    No Known Activations