© 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. 128248
    Prev
    Next
    INDEX
    Explanations

    Redistributions of source code

    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
    Not in Any Lists

    No Comments

    Negative Logits
     contributes
    -0.06
     ideology
    -0.06
     participer
    -0.06
     helps
    -0.06
     योजना
    -0.06
    وال
    -0.06
    unified
    -0.06
     nutrient
    -0.06
     organizes
    -0.06
    следова
    -0.06
    POSITIVE LOGITS
     أمام
    0.07
     ჩვენ
    0.06
     naše
    0.06
    婍
    0.06
     unsere
    0.06
     SEA
    0.06
     tatsächlich
    0.06
     cidades
    0.06
     हमारी
    0.06
    私は
    0.06
    Activations Density 0.002%

    No Known Activations