© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 3631
    Prev
    Next
    INDEX
    Explanations

    hormone levels

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

    terms and identifiers that might appear in digital or technical content, including hormone names, usernames, and UI elements.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on tokens that appear in major section titles or headings (e.g. document or article 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_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
    0
    -1.70
     it
    -1.70
     Многие
    -1.61
     what
    -1.58
    3
    -1.57
    4
    -1.53
     normalen
    -1.46
    吵
    -1.36
     Когда
    -1.34
     abertura
    -1.34
    POSITIVE LOGITS
     BERNAMA
    1.66
    ↩
    1.63
    🐕
    1.56
     maxime
    1.54
    nemia
    1.54
     stund
    1.52
    
    1.46
     daca
    1.46
    <0x00>
    1.45
     aix
    1.45
    Activations Density 0.108%

    No Known Activations