© 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. 12789
    Prev
    Next
    INDEX
    Explanations

    patients and dates

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

    This neuron fires on section‐ or title‐level punctuation markers—especially colons, question marks, and similar delimiting symbols used to separate titles, subtitles, or section headings.

    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
     chré
    -1.39
     яйцо
    -1.27
     掃除
    -1.27
     to
    -1.26
    皈
    -1.08
     бого
    -1.05
     what
    -1.05
     terrestrial
    -1.04
    世间
    -1.03
     vật
    -1.02
    POSITIVE LOGITS
    ֶּ
    1.51
    ַּ
    1.49
    ּוֹ
    1.47
    ִּ
    1.45
     outcome
    1.41
    pared
    1.33
    ְּ
    1.33
     questionnaire
    1.27
     patients
    1.27
     bụ
    1.20
    Activations Density 0.549%

    No Known Activations