© 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-3-12B
    5. 12-GEMMASCOPE-2-RES-16K
    7. 18
    Prev
    Next
    INDEX
    Explanations

    nth, th

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_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
    ৯
    1.14
    २
    1.01
     ощущение
    0.97
     llena
    0.93
     veliko
    0.90
     бонусы
    0.89
    ுகிற
    0.89
     ذریع
    0.89
     sociali
    0.88
     altri
    0.87
    POSITIVE LOGITS
    r
    1.22
    ש
    1.16
    ر
    1.14
    k
    1.09
    v
    1.04
    j
    1.01
    là
    0.98
    pé
    0.98
    c
    0.98
    رر
    0.95
    Activations Density 0.059%

    No Known Activations