© 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. 2821
    Prev
    Next
    INDEX
    Explanations

    csv and abbreviations

    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
    isChecked
    2.96
     vă
    2.83
    +}^{
    2.82
     lapsed
    2.82
     volver
    2.82
    setCellValue
    2.68
     obvious
    2.68
     swoim
    2.57
     shame
    2.57
     तबीयत
    2.56
    POSITIVE LOGITS
    в
    4.44
    ्ह
    4.22
    olution
    3.41
    v
    3.37
    क़्त
    3.33
    vy
    3.22
    ැනි
    3.18
    ulnerable
    3.17
    ्हे
    3.17
    Cet
    3.10
    Activations Density 0.718%

    No Known Activations