© 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-262K
    7. 42994
    Prev
    Next
    INDEX
    Explanations

    peer-reviewed publications and research

    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_262k_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
    ا
    2.72
    り
    1.92
    вання
    1.87
    부터
    1.77
    ení
    1.70
    ﺍ
    1.62
    ка
    1.61
    いた
    1.59
    客様
    1.59
    しないで
    1.57
    POSITIVE LOGITS
    ت
    1.94
    Е
    1.67
     </
    1.48
    1.42
    ]]></
    1.38
    Bac
    1.34
     stoked
    1.34
     Архивная
    1.33
    Пре
    1.32
     Nähe
    1.32
    Activations Density 0.002%

    No Known Activations