© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 10116
    Prev
    Next
    INDEX
    Explanations

    . (program code)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    י
    1.08
    旯
    1.04
     Bevölkerung
    1.02
     riguardo
    1.02
     gek
    1.00
    áciu
    1.00
    ل
    0.99
     rekla
    0.98
    썹
    0.98
     кантип
    0.97
    POSITIVE LOGITS
    '
    0.80
    They
    0.79
     می‌ده
    0.79
     consom
    0.77
    هم
    0.76
    ()'
    0.75
    Anti
    0.74
    are
    0.73
    Russian
    0.73
    Iron
    0.73
    Activations Density 0.146%

    No Known Activations