© 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. 10-GEMMASCOPE-RES-131K
    7. 39387
    Prev
    Next
    INDEX
    Explanations

    section and its designation

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

    This neuron detects document section markers and numbered heading identifiers (e.g. “Sec,” braces with numbers, and section-number formatting).

    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
    That
    -1.58
    髑
    -1.38
    ходит
    -1.30
    that
    -1.28
     just
    -1.28
     without
    -1.28
    ....
    -1.23
     for
    -1.23
     ....
    -1.20
    just
    -1.20
    POSITIVE LOGITS
     about
    2.44
    ！」
    1.44
     reinst
    1.41
     دیگران
    1.38
     innumer
    1.37
    !!!)
    1.35
    偁
    1.34
     $\&$
    1.33
    ”!
    1.32
     parece
    1.31
    Activations Density 0.110%

    No Known Activations