© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 16228
    Prev
    Next
    INDEX
    Explanations

    Gain

    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
    PROBLE
    1.98
    filenames
    1.88
    ف
    1.88
     paquetes
    1.88
    ৪
    1.87
    गतान
    1.86
     subsections
    1.85
     provoqu
    1.83
     acumul
    1.81
    bookmarks
    1.80
    POSITIVE LOGITS
    ্লাহ
    1.66
    де
    1.63
     وعلى
    1.63
     어
    1.58
    ية
    1.55
    ę
    1.55
    ah
    1.55
    នឹង
    1.47
    bei
    1.46
     oat
    1.45
    Activations Density 0.011%

    No Known Activations