© 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. 10-GEMMASCOPE-RES-131K
    7. 40471
    Prev
    Next
    INDEX
    Explanations

    concentration, historical development

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

    This neuron detects subword fragments created by hyphenation (tokens ending or beginning with a hyphen).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     even
    -1.66
     only
    -1.62
     =
    -1.47
     many
    -1.47
     also
    -1.43
     sowohl
    -1.37
     all
    -1.36
    A
    -1.36
     being
    -1.36
    There
    -1.35
    POSITIVE LOGITS
    "",
    1.61
     inmiddels
    1.29
     雰囲気
    1.29
    出版年
    1.28
    жнарод
    1.28
    brakk
    1.27
     toolStrip
    1.23
     Conscious
    1.23
    儸
    1.23
     hecta
    1.22
    Activations Density 0.024%

    No Known Activations