© 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-16K
    7. 2883
    Prev
    Next
    INDEX
    Explanations

    level of detail or design

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ي
    4.03
    比如
    3.13
    ி
    3.12
    美元
    3.07
    ি
    3.03
     размеры
    2.79
    en
    2.74
    %\
    2.70
    ينا
    2.66
    ی
    2.65
    POSITIVE LOGITS
    с
    3.43
    ु
    3.12
    то
    3.03
    izer
    2.96
    曙
    2.87
    ise
    2.67
     eb
    2.63
    סף
    2.58
    व्यवस्था
    2.57
    턴
    2.51
    Activations Density 0.113%

    No Known Activations