© 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. 128237
    Prev
    Next
    INDEX
    Explanations

    youtube links

    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
     normalmente
    -0.07
     as
    -0.07
    normally
    -0.06
     normaal
    -0.06
     nunca
    -0.06
    Normally
    -0.06
     normalerweise
    -0.06
     Normally
    -0.06
     normally
    -0.06
     habitually
    -0.06
    POSITIVE LOGITS
     യ
    0.06
     demonstrates
    0.06
    ではなく
    0.06
     doesn
    0.06
    числения
    0.06
    参考文献
    0.06
    पर्यंत
    0.06
     রাষ্ট্রের
    0.06
     (!
    0.06
     صور
    0.06
    Activations Density 0.001%

    No Known Activations