© 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. 120907
    Prev
    Next
    INDEX
    Explanations

    fascicular, type, of, adapting, former

    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
     on
    -0.08
    鎖
    -0.06
     sites
    -0.06
     estad
    -0.06
     different
    -0.06
     iga
    -0.06
     সম্মেল
    -0.06
     Eagle
    -0.06
     通过
    -0.06
     required
    -0.05
    POSITIVE LOGITS
     オフィス
    0.07
     těž
    0.06
     শুধ
    0.06
     mixed
    0.06
    オフィス
    0.06
     dosen
    0.06
     כ
    0.06
     aerospace
    0.06
     demostrar
    0.06
     añadir
    0.06
    Activations Density 0.001%

    No Known Activations