© 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-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3278
    Prev
    Next
    INDEX
    Explanations

    SQL FROM or file format

    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
    ти
    2.20
    ن
    2.08
    торов
    1.98
    ่
    1.76
    प
    1.67
    Ook
    1.65
    erves
    1.63
    it
    1.63
     Eğ
    1.62
    ون
    1.56
    POSITIVE LOGITS
    них
    1.99
    ties
    1.80
    خ
    1.75
    യ്യാ
    1.73
    יה
    1.68
    ја
    1.66
    !*\
    1.59
    ון
    1.56
    ных
    1.55
    cough
    1.55
    Activations Density 0.395%

    No Known Activations