© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 15997
    Prev
    Next
    INDEX
    Explanations

    security keys, restaurant, solutions

    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
     is
    1.46
     in
    1.42
     (
    1.35
     from
    1.31
    ,
    1.29
    ,"
    1.26
     it
    1.23
     are
    1.23
     has
    1.20
     of
    1.19
    POSITIVE LOGITS
    ﺴ
    1.04
     решений
    0.96
    েনারেল
    0.95
    ल्पनिक
    0.94
    produtos
    0.92
    ﺪ
    0.92
    avascript
    0.91
    ﺳ
    0.91
    tractor
    0.90
     aeron
    0.90
    Activations Density 0.023%

    No Known Activations