© 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. 71921
    Prev
    Next
    INDEX
    Explanations

    quantifiers and categories

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

    The neuron fires on tokens that express quantities or counts (numbers, quantifiers, “many,” “one,” “how many,” 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
    踯
    -1.69
    NING
    -1.62
    僰
    -1.59
     susc
    -1.55
    糴
    -1.52
    ATIVA
    -1.52
    sistent
    -1.51
     недавно
    -1.50
     唯美
    -1.49
    elegant
    -1.47
    POSITIVE LOGITS
     in
    1.66
    </strong>
    1.57
     -
    1.45
     through
    1.36
     então
    1.35
     his
    1.34
    色が
    1.33
     unspeakable
    1.31
     also
    1.31
     男子
    1.30
    Activations Density 0.003%

    No Known Activations