© 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. 29031
    Prev
    Next
    INDEX
    Explanations

    embryology, callable, RRP

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

    company or product names in technical and scientific contexts.

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

    The neuron is triggered by standalone named‐entity or acronym‐style tokens (e.g. brand names, technical identifiers, all‐caps abbreviations).

    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
    嗵
    -3.20
    
    -3.13
    鉏
    -3.11
    跸
    -3.06
    ︕
    -3.03
    佧
    -2.75
    
    -2.73
    錀
    -2.66
    ᕱ
    -2.64
    荜
    -2.64
    POSITIVE LOGITS
    [
    3.86
    .
    3.66
    (
    3.47
    <
    3.00
     Their
    2.97
    "
    2.92
    er
    2.86
     It
    2.84
    ’
    2.78
     These
    2.73
    Activations Density 0.033%

    No Known Activations