© 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. 128062
    Prev
    Next
    INDEX
    Explanations

    arranged by country or context

    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
    ria
    -0.06
    TotalPrice
    -0.05
    utils
    -0.05
     True
    -0.05
    ó
    -0.05
    GAR
    -0.05
     Bahasa
    -0.05
     зві
    -0.05
     আক্রমণের
    -0.05
     സമ്പ
    -0.05
    POSITIVE LOGITS
     doen
    0.07
    㥽
    0.07
     OTHER
    0.07
     doesn
    0.07
     direkte
    0.07
    㧣
    0.07
    Wenn
    0.06
     wenn
    0.06
     như
    0.06
     δεν
    0.06
    Activations Density 0.006%

    No Known Activations