© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 45004
    Prev
    Next
    INDEX
    Explanations

    staff, faculty, cast, team members

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

    The neuron activates on words naming organizational roles or groups of people (e.g. “staff,” “member,” “faculty”).

    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
            
    -1.55
    ichtete
    -1.42
    ichteten
    -1.36
    mutual
    -1.36
    ishable
    -1.34
    examined
    -1.31
    ERICAL
    -1.30
    deckte
    -1.29
    delser
    -1.29
    ()][
    -1.28
    POSITIVE LOGITS
     bidra
    1.53
     member
    1.38
     such
    1.37
     cláus
    1.34
    “
    1.33
     who
    1.30
     cuivre
    1.25
     أيضا
    1.25
    在我们
    1.25
    end
    1.24
    Activations Density 0.072%

    No Known Activations