© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 35678
    Prev
    Next
    INDEX
    Explanations

    staff, personnel, or members

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

    The neuron activates on numeric expressions and quantity/measure words (counts, digits, “all,” “twice,” 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_22/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
    病人
    -1.30
    🌂
    -1.25
    uração
    -1.17
    насе
    -1.14
     When
    -1.13
    にほんブログ村
    -1.13
     sebenar
    -1.13
     getObject
    -1.12
     Industrie
    -1.09
     mücade
    -1.09
    POSITIVE LOGITS
     staff
    2.03
     who
    1.71
     team
    1.66
     employees
    1.63
     members
    1.62
     senior
    1.49
     employee
    1.38
     leadership
    1.35
     reparación
    1.29
     junior
    1.27
    Activations Density 0.053%

    No Known Activations