© 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. 2772
    Prev
    Next
    INDEX
    Explanations

    describing states and qualities

    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
    त
    1.32
    ❤❤
    1.28
    %%%%%%%%%%%%
    1.27
     marginTop
    1.25
    d
    1.25
    री
    1.23
    찧
    1.23
    fqsen
    1.21
    一级
    1.18
    ()<<
    1.17
    POSITIVE LOGITS
    তা
    1.62
    <bos>
    1.31
    ских
    1.24
    ak
    1.24
     nope
    1.20
    اش
    1.20
     hizo
    1.19
    أس
    1.17
     înce
    1.17
     podía
    1.17
    Activations Density 0.374%

    No Known Activations