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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 40357
    Prev
    Next
    INDEX
    Explanations

    drawing, segments, questions, American History

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

    This neuron activates on numeric expressions—Arabic numerals, spelled‐out numbers, and Roman numerals indicating dates, list items, or section/segment labels.

    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
     also
    -1.19
     this
    -1.10
     if
    -1.09
     também
    -1.09
     as
    -1.07
     PROCEEDINGS
    -1.06
     their
    -1.06
     серпня
    -1.04
     creando
    -1.04
     (
    -1.03
    POSITIVE LOGITS
     alcune
    1.16
    garanti
    1.14
     vermag
    1.13
     molho
    1.12
     beijo
    1.11
    MIDDLEWARE
    1.09
    𞤤
    1.09
    stö
    1.09
    lllllllll
    1.08
     löst
    1.08
    Activations Density 0.004%

    No Known Activations