© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1869
    Prev
    Next
    INDEX
    Explanations

    examine, process, understand

    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_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
    ലം
    0.87
    ものを
    0.86
    物を
    0.85
    於
    0.82
    ையை
    0.82
     را
    0.81
    திகளை
    0.80
    ್‌
    0.80
     Pada
    0.78
    Pada
    0.77
    POSITIVE LOGITS
    le
    0.80
     planned
    0.75
     lest
    0.71
    achadh
    0.67
    ว่าเป็น
    0.66
     extract
    0.66
     downwards
    0.65
    কারণ
    0.65
     downward
    0.64
     sobald
    0.64
    Activations Density 0.167%

    No Known Activations