© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 79656
    Prev
    Next
    INDEX
    Explanations

    staff, team, and volunteers

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

    The neuron activates on words naming groups of people (e.g. staff, team, personnel, crew, officers).

    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
    不同
    -1.21
     zostać
    -1.08
     שהוא
    -1.08
    事
    -1.05
    נוּ
    -1.05
     Different
    -1.05
     different
    -1.05
    ǚ
    -1.03
    dą
    -1.02
    不同的
    -1.01
    POSITIVE LOGITS
     of
    2.39
     at
    1.85
     who
    1.57
     from
    1.51
    bánh
    1.29
    bouncycastle
    1.17
     semua
    1.11
     including
    1.09
     drenaje
    1.02
     trabalhadores
    1.02
    Activations Density 0.007%

    No Known Activations