© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 4903
    Prev
    Next
    INDEX
    Explanations

    list item intros

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_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
    п
    0.54
    ें
    0.53
    -
    0.53
     =
    0.53
    ๆ
    0.52
    ir
    0.52
    se
    0.51
    fect
    0.51
    ጮ
    0.50
     вступи
    0.50
    POSITIVE LOGITS
    라우
    0.98
     submodule
    0.92
    ✄
    0.88
    Practice
    0.88
     별
    0.85
    یاط
    0.85
     molybdenum
    0.85
    <unused1831>
    0.84
     하시
    0.83
    Associate
    0.82
    Activations Density 0.055%

    No Known Activations