© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103823
    Prev
    Next
    INDEX
    Explanations

    Woodward, formaldehyde, Bonn, Wilkes

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

    names of people, organizations, and places in formal or academic documents.

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

    The neuron selectively activates on named entities and technical terms—proper names (people, places, authors) and chemical compound names.

    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
     \
    -3.20
     {
    -3.00
    ︲
    -2.61
    2
    -2.56
    ный
    -2.47
     avec
    -2.45
     "
    -2.36
    ًا
    -2.33
    ',
    -2.27
    '
    -2.27
    POSITIVE LOGITS
    ?”
    3.33
    廰
    2.48
    嚶
    2.30
    頻繁
    2.23
     вопроса
    2.23
    /');
    2.23
    ྕ
    2.22
    羕
    2.20
    derdag
    2.19
     jsi
    2.19
    Activations Density 0.003%

    No Known Activations