© 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. 12525
    Prev
    Next
    INDEX
    Explanations

    main ():

    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
    es
    2.04
    ル
    1.99
    ً
    1.96
    k
    1.93
     tinggi
    1.80
    اتها
    1.80
    etem
    1.79
     üks
    1.78
    c
    1.78
    enya
    1.77
    POSITIVE LOGITS
    ги
    2.72
     recessed
    2.43
    ఒ
    2.31
    land
    2.21
     bliss
    2.15
    duced
    2.10
    ../../
    2.10
    described
    2.06
     evidenced
    1.96
    oltre
    1.95
    Activations Density 0.016%

    No Known Activations