© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128127
    Prev
    Next
    INDEX
    Explanations

    court cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ipad
    -0.06
     Św
    -0.06
     unquestionably
    -0.06
     preamp
    -0.06
    ipad
    -0.06
    minute
    -0.06
     sendiri
    -0.06
     colloidal
    -0.06
     Provinsi
    -0.06
     Vorteile
    -0.06
    POSITIVE LOGITS
     उसके
    0.06
     jeho
    0.06
     on
    0.06
     jego
    0.06
     sogenannte
    0.05
     innoc
    0.05
     해당
    0.05
    regarding
    0.05
    ”:
    0.05
     गार
    0.05
    Activations Density 0.002%

    No Known Activations