© 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. 116161
    Prev
    Next
    INDEX
    Explanations

    Kafelnikov Dominik

    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
    ajana
    -0.06
     cyl
    -0.06
     several
    -0.06
    approximately
    -0.06
     approximately
    -0.06
     two
    -0.06
     birçok
    -0.06
     verschillende
    -0.06
    他們的
    -0.06
     MongoDB
    -0.06
    POSITIVE LOGITS
     to
    0.08
     incluido
    0.06
     каждую
    0.06
     方法
    0.06
     μαζί
    0.06
     এনে
    0.06
     incluidos
    0.06
    方法
    0.06
     புதிய
    0.06
    회를
    0.06
    Activations Density 0.001%

    No Known Activations