© 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. 120845
    Prev
    Next
    INDEX
    Explanations

    lover and fan

    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
     bitter
    -0.06
     disponer
    -0.06
    estas
    -0.06
    onDidChange
    -0.06
     lauded
    -0.06
     storied
    -0.06
    ερμαν
    -0.06
     W
    -0.06
    डले
    -0.06
     lze
    -0.06
    POSITIVE LOGITS
    从小
    0.07
     так
    0.06
     যুব
    0.06
     Substitute
    0.06
    所以
    0.06
    Allora
    0.06
    coerce
    0.06
    স্তন
    0.06
     दोन्ही
    0.06
     поэтому
    0.06
    Activations Density 0.036%

    No Known Activations