© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 1528
    Prev
    Next
    INDEX
    Explanations

    RF, AF, Optional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-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
     (
    1.35
    .
    0.93
    (
    0.83
     factors
    0.81
     ([
    0.67
    தாகும்
    0.62
     ((
    0.57
    （
    0.52
     ovat
    0.51
     (=
    0.47
    POSITIVE LOGITS
    см
    3.50
    ,)
    3.42
    اخت
    3.34
    или
    3.31
    وه
    3.23
    ?),
    3.17
    жен
    3.16
    роди
    3.15
    без
    3.14
    хо
    3.14
    Activations Density 0.491%

    No Known Activations