© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 26587
    Prev
    Next
    INDEX
    Explanations

    people, workers, and stakeholders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ᱖
    0.54
    ："
    0.49
    、「
    0.49
    至少
    0.48
    зия
    0.47
    有可能
    0.46
    >≥</
    0.46
    数は
    0.46
    лия
    0.44
    樎
    0.43
    POSITIVE LOGITS
     orchestrated
    0.59
     Canva
    0.54
     HubSpot
    0.53
     onboarding
    0.52
     marketers
    0.50
     orchestr
    0.50
     pracowników
    0.50
     människor
    0.49
     reps
    0.48
     Airbnb
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.