© 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. 129950
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on tokens that serve as enumerators or numbered‐item markers—e.g. list/volume numbers (“No.”, “(1)”), section indicators (“to” in “prior art to the claims”), headings/dates (“WEEKLY IN”), and similar enumeration cues.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    text punctuation and foreign characters

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     maal
    -1.09
    daging
    -0.93
     пищи
    -0.90
    IANE
    -0.90
    closeButton
    -0.88
     onlyOwner
    -0.88
    groet
    -0.86
    anı
    -0.85
     Meksi
    -0.85
     désactiv
    -0.85
    POSITIVE LOGITS
     uitzicht
    1.16
    会出现
    1.15
    èvement
    1.13
    ـ
    1.07
    inerario
    1.07
     يول
    1.07
    ara
    1.06
    ύ
    1.06
    濒
    1.05
    braio
    1.02
    Activations Density 0.000%

    No Known Activations