© 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. 120915
    Prev
    Next
    INDEX
    Explanations

    bracketed numbers

    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
    9
    -0.06
     з
    -0.06
     P
    -0.06
    clean
    -0.06
    now
    -0.06
     ahorita
    -0.06
    6
    -0.06
     M
    -0.06
    现在
    -0.05
     selon
    -0.05
    POSITIVE LOGITS
     expectativa
    0.07
     nekoliko
    0.07
     ряд
    0.06
     précédentes
    0.06
    従来の
    0.06
     birkaç
    0.06
     nakon
    0.06
     após
    0.06
     is
    0.06
     dopo
    0.06
    Activations Density 0.009%

    No Known Activations