© 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. 12479
    Prev
    Next
    INDEX
    Explanations

    explica, every, would, and

    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
    existent
    1.23
    Vad
    1.13
    ကြား
    1.11
     $("<
    1.11
    deferred
    1.10
    ी
    1.10
    wheeled
    1.08
     squeezing
    1.06
    طار
    1.06
     ballroom
    1.06
    POSITIVE LOGITS
    en
    1.38
    s
    1.37
    rk
    1.32
     publica
    1.31
    re
    1.29
     teht
    1.26
     Agama
    1.24
     aí
    1.24
     gini
    1.22
     explica
    1.21
    Activations Density 0.000%

    No Known Activations