© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72979
    Prev
    Next
    INDEX
    Explanations

    Sheppard

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

    The neuron is keyed to pick out tokens containing consecutive repeated letters (e.g. “weeping,” “seepage,” “Sheppard,” “Newsweek”).

    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
     apolog
    -2.91
    谞
    -2.70
    澐
    -2.61
     has
    -2.53
     ensures
    -2.50
     blatantly
    -2.50
     为什么
    -2.48
     maneuver
    -2.38
    𓍯
    -2.38
    罂
    -2.34
    POSITIVE LOGITS
     представителей
    2.72
     stalwart
    2.47
     MAJOR
    2.42
     
    2.25
    噠
    2.11
     البته
    2.09
    ians
    2.09
    pecabe
    2.08
    n
    2.06
    would
    2.05
    Activations Density 0.001%

    No Known Activations