© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73564
    Prev
    Next
    INDEX
    Explanations

    Edison and neurosurgery

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

    The neuron is responding to formal names of institutions or specialized technical fields (e.g. “Edison Laboratory,” “Thomas Edison,” “neurosurgical”).

    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
    .
    -2.77
    t
    -2.67
    ”.
    -2.52
     Our
    -2.44
    m
    -2.30
    ING
    -2.23
    test
    -2.23
     -
    -2.23
     Need
    -2.22
     üblichen
    -2.20
    POSITIVE LOGITS
    ᠌
    3.22
    ⚋
    2.45
    コチラ
    2.41
    ｄ
    2.33
    횃
    2.30
     stihl
    2.27
     sözler
    2.27
    鋱
    2.25
    诹
    2.25
    ・「
    2.25
    Activations Density 0.009%

    No Known Activations