© 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-16K
    7. 3787
    Prev
    Next
    INDEX
    Explanations

    non-latin script encountered

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    េង
    0.69
    ന്‍സ്
    0.67
     oranges
    0.66
    ⌀
    0.63
    chil
    0.63
     Din
    0.63
     कामका
    0.62
    刂
    0.62
     zł
    0.62
     Autón
    0.62
    POSITIVE LOGITS
    bone
    0.70
     mor
    0.69
     ಪಕ್ಷ
    0.65
    楢
    0.60
     puffed
    0.60
    humid
    0.59
    Michelle
    0.59
    ComboBox
    0.59
    ంప
    0.59
    եք
    0.59
    Activations Density 0.112%

    No Known Activations