© 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-262K
    7. 5177
    Prev
    Next
    INDEX
    Explanations

    EMIEW2, EMIEW3, Maze

    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
     affectionately
    1.79
     tannins
    1.40
    挲
    1.36
     appellee
    1.34
    ভৌম
    1.31
     extraordinaire
    1.31
    ्वती
    1.30
    θηκε
    1.30
    если
    1.30
    ﯽ
    1.28
    POSITIVE LOGITS
    )
    1.91
    {
    1.83
    `
    1.69
    ޢ
    1.55
    ı
    1.54
    \
    1.48
    li
    1.47
    ),
    1.45
    Firing
    1.43
    $
    1.43
    Activations Density 0.002%

    No Known Activations