© 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. 120872
    Prev
    Next
    INDEX
    Explanations

    Iranian preachers, Solar energy, writer

    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
    тына
    -0.07
    ئين
    -0.07
     others
    -0.07
    等を
    -0.06
     степен
    -0.06
    ılmıştır
    -0.06
    においては
    -0.06
    ेंसिल
    -0.06
    與
    -0.06
    防止
    -0.06
    POSITIVE LOGITS
     coincident
    0.06
     विकार
    0.06
     samtidigt
    0.06
     maravilloso
    0.06
    மாக
    0.06
     unang
    0.06
     participan
    0.06
    '
    0.05
    but
    0.05
     DEVICES
    0.05
    Activations Density 0.001%

    No Known Activations