© 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. 29-GEMMASCOPE-2-RES-65K
    7. 2088
    Prev
    Next
    INDEX
    Explanations

    person names

    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_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     M
    0.35
    M
    0.32
    ino
    0.30
     re
    0.29
    آ
    0.28
    I
    0.28
    ich
    0.28
    ise
    0.28
     皆
    0.27
     all
    0.27
    POSITIVE LOGITS
    vykor
    0.48
    <unused976>
    0.45
     Chương
    0.45
    ANGMAR
    0.45
     chương
    0.45
     Thackeray
    0.45
    ঙ্কর
    0.44
    ouvoir
    0.44
    ដ្ឋាន
    0.44
    иск
    0.44
    Activations Density 0.070%

    No Known Activations