© 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. 87407
    Prev
    Next
    INDEX
    Explanations

    rechargeable batteries; gene overexpression

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

    The neuron detects forms of protein or gene "overexpression" in scientific or medical contexts.

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

    The neuron responds strongly to long, technical compound words typical in scientific writing (e.g. “rechargeable” and “overexpression”).

    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
     моя
    -2.47
    what
    -2.45
    带有
    -2.41
    ~。
    -2.38
    ~♪
    -2.36
    柃
    -2.34
    mė
    -2.27
    ╹
    -2.23
    ~!
    -2.20
    ’,
    -2.20
    POSITIVE LOGITS
    '
    3.78
    (
    2.55
    <
    2.52
    —
    2.48
     unfailing
    2.45
    *
    2.44
    [
    2.42
    _
    2.39
     Tiefe
    2.36
     Geset
    2.33
    Activations Density 0.003%

    No Known Activations