© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10420
    Prev
    Next
    INDEX
    Explanations

    stormwater control, keyboard shortcuts, Rain Element

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    Спо
    0.68
    ../../
    0.66
    ما
    0.65
    ЛИ
    0.65
    ि
    0.63
    від
    0.60
    াতার
    0.60
    Examin
    0.60
    toRadians
    0.59
    ante
    0.59
    POSITIVE LOGITS
    zonych
    1.04
     downside
    0.99
     drawback
    0.97
     elucid
    0.93
    <0xD5>
    0.92
    tics
    0.89
    也能
    0.89
    𝑡
    0.89
     餐
    0.87
    Stabilise
    0.86
    Activations Density 0.067%

    No Known Activations