© 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. 127978
    Prev
    Next
    INDEX
    Explanations

    spokesperson or spokesman

    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
    ที่
    -0.07
     koriste
    -0.06
    უს
    -0.06
     सफेद
    -0.06
     nera
    -0.06
     použí
    -0.06
     ataupun
    -0.06
     whites
    -0.06
     dane
    -0.06
     எதிர
    -0.06
    POSITIVE LOGITS
     sensual
    0.06
     {(
    0.06
     दृश्य
    0.06
     reluctantly
    0.06
    andus
    0.06
     ততদিন
    0.05
     unless
    0.05
     estará
    0.05
     pard
    0.05
     sẽ
    0.05
    Activations Density 0.009%

    No Known Activations