© 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. 99621
    Prev
    Next
    INDEX
    Explanations

    Edmonton, Bentley, DMS, subspecies

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

    This neuron detects proper‐name tokens—specific capitalized entities such as brands, place names, class or API names, etc.

    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
    呖
    -2.75
    <bos>
    -2.47
    uſe
    -2.45
     conocida
    -2.44
    ing
    -2.30
    作品の
    -2.23
     ─
    -2.22
    轳
    -2.19
    鹩
    -2.16
    纡
    -2.13
    POSITIVE LOGITS
    m
    2.89
     We
    2.83
    o
    2.69
    d
    2.59
    {
    2.58
    ).
    2.55
    a
    2.42
    j
    2.31
     avec
    2.27
     enfrentan
    2.19
    Activations Density 0.008%

    No Known Activations