© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 12291
    Prev
    Next
    INDEX
    Explanations

    directions to regions

    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
    Negative Logits
    र
    4.33
    ار
    4.21
    ist
    3.72
    er
    3.28
    ো
    3.24
    ção
    3.12
    ৭
    2.88
    ../
    2.87
    zelfde
    2.84
    л
    2.83
    POSITIVE LOGITS
    site
    3.03
    s
    2.91
    ्स
    2.86
    sides
    2.81
    making
    2.76
    amphetamine
    2.73
    manship
    2.70
    tttt
    2.66
    ়া
    2.58
    ség
    2.56
    Activations Density 0.016%

    No Known Activations