© 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. 148420
    Prev
    Next
    INDEX
    Explanations

    filing, work, difference, conditions, insights

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

    social dynamics and traits

    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
     الدكتور
    0.54
     الفرنسي
    0.49
     فرانس
    0.49
    解釋
    0.48
     الفرنس
    0.48
     élément
    0.47
    বিচার
    0.47
    靘
    0.47
     เอ่อ
    0.47
     ايضا
    0.46
    POSITIVE LOGITS
     Mobility
    0.50
     Tribes
    0.49
     Initi
    0.48
     Women
    0.47
     Driving
    0.46
    を集
    0.46
     Mixed
    0.45
     Kin
    0.45
     Wheels
    0.44
     Warm
    0.44
    Activations Density 0.000%

    No Known Activations