© 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. 41-GEMMASCOPE-2-RES-16K
    7. 3075
    Prev
    Next
    INDEX
    Explanations

    potential actions

    np_max-act-logits · gemini-2.5-flash-lite

    word endings

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_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
    งาน
    0.73
    ბ
    0.72
    work
    0.70
    un
    0.70
    will
    0.69
    was
    0.66
    wide
    0.66
    works
    0.64
    w
    0.64
    ning
    0.63
    POSITIVE LOGITS
    fficial
    1.39
    ğlu
    1.38
    pportun
    1.33
    pportunities
    1.30
    pped
    1.30
    pping
    1.28
    oooo
    1.27
    ooo
    1.19
    oooooooo
    1.19
    등학교
    1.09
    Activations Density 0.710%

    No Known Activations