© 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. 116183
    Prev
    Next
    INDEX
    Explanations

    all followed by of, have, or these

    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
    Not in Any Lists

    No Comments

    Negative Logits
     هیچ
    -0.07
     nessun
    -0.07
     ไม่มี
    -0.07
     mengenai
    -0.07
    齐全
    -0.07
    efficacité
    -0.06
     никаких
    -0.06
    ংখ্যান
    -0.06
    闗
    -0.06
    🚫
    -0.06
    POSITIVE LOGITS
     you
    0.06
     these
    0.06
    ط
    0.06
     overcoming
    0.05
     your
    0.05
    this
    0.05
    为主
    0.05
     getting
    0.05
     awfully
    0.05
    target
    0.05
    Activations Density 0.008%

    No Known Activations