© 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. 34-GEMMASCOPE-RES-131K
    7. 34976
    Prev
    Next
    INDEX
    Explanations

    ODI, IST, Q:

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

    This neuron detects structured metadata and section headings—timestamps, dates, labels like "Overview" or "Where to Watch Live," and similar document‐section markers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     goto
    -0.82
     seemingly
    -0.79
     supplied
    -0.78
    خواندن
    -0.77
     cellulose
    -0.74
     紙
    -0.72
    مثلة
    -0.71
    giai
    -0.71
    mond
    -0.71
     related
    -0.71
    POSITIVE LOGITS
    ïs
    0.88
    鹉
    0.84
    wardship
    0.82
     ಬ
    0.81
    美
    0.79
    úmenes
    0.75
    lahraga
    0.75
    bidity
    0.72
    wd
    0.71
     trunc
    0.71
    Activations Density 0.011%

    No Known Activations