© 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. 9796
    Prev
    Next
    INDEX
    Explanations

    `!` or `"` followed by certain tokens

    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
    ம்
    3.00
    o
    2.95
    л
    2.91
    ed
    2.85
    al
    2.79
    e
    2.70
    ে
    2.66
    ه
    2.66
    ../../
    2.45
    त
    2.41
    POSITIVE LOGITS
     او
    2.38
     supérieur
    2.37
    さて
    2.37
     beau
    2.36
    கள்
    2.34
    ⲟ
    2.33
     šte
    2.31
    òng
    2.29
    uterine
    2.23
     eigen
    2.18
    Activations Density 0.129%

    No Known Activations