© 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. 18151
    Prev
    Next
    INDEX
    Explanations

    organizational division or department names

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

    company divisions or segments

    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
    glichkeiten
    0.45
    ี่
    0.44
    两国
    0.42
    Tarea
    0.42
    utérus
    0.42
    ceo
    0.41
     থাকতে
    0.41
    愊
    0.41
     প্রার্থ
    0.40
    是一家
    0.40
    POSITIVE LOGITS
     division
    0.88
     Division
    0.83
    部門
    0.80
    division
    0.73
    Division
    0.69
     department
    0.67
     DIVISION
    0.63
     подразде
    0.57
     डिवीजन
    0.57
     división
    0.55
    Activations Density 0.286%

    No Known Activations