© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 128144
    Prev
    Next
    INDEX
    Explanations

    documentation tags

    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
     petite
    -0.07
    itage
    -0.07
    的小
    -0.06
     происходит
    -0.06
     Containing
    -0.06
     झालेले
    -0.06
     Solubility
    -0.06
     containing
    -0.06
     thay
    -0.06
    的那
    -0.06
    POSITIVE LOGITS
     Fake
    0.06
     वेबसाईट
    0.06
     تلاش
    0.06
     cases
    0.05
     toujours
    0.05
     trot
    0.05
    espec
    0.05
    也就是
    0.05
     যতটুকু
    0.05
     क्षमताओं
    0.05
    Activations Density 0.001%

    No Known Activations