© 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-262K
    7. 5450
    Prev
    Next
    INDEX
    Explanations

    wrapping up

    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_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
    ايا
    1.47
     commemorate
    1.28
    ه
    1.25
    dür
    1.24
    န်
    1.22
    veel
    1.18
    ু
    1.17
     transversely
    1.16
    neho
    1.15
    Ფ
    1.15
    POSITIVE LOGITS
    K
    1.15
     K
    1.08
    उप
    1.04
     оби
    1.00
    ers
    0.99
     Hoa
    0.98
    Wrapping
    0.94
     up
    0.93
    ように
    0.92
    쯤
    0.88
    Activations Density 0.080%

    No Known Activations