© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1920
    Prev
    Next
    INDEX
    Explanations

    roles and titles of individuals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
     suatu
    1.33
    Ǘ
    1.21
     સંખ્યા
    1.18
     صغيرة
    1.18
    ॉर्क
    1.18
     dvě
    1.17
     sogenannten
    1.15
     사용하여
    1.13
     sogenannte
    1.13
    勰
    1.12
    POSITIVE LOGITS
     and
    1.09
     heaped
    1.00
     pathways
    0.99
     Heidi
    0.98
     potholes
    0.98
     gets
    0.95
    opter
    0.93
    and
    0.93
     should
    0.92
     could
    0.91
    Activations Density 0.223%

    No Known Activations