© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 128053
    Prev
    Next
    INDEX
    Explanations

    phrases following punctuation

    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
     he
    -0.06
     merely
    -0.06
     नेत्र
    -0.06
    handlungen
    -0.06
    他
    -0.06
     presumably
    -0.06
     simplemente
    -0.06
    ನ್
    -0.06
     যারা
    -0.06
     σε
    -0.05
    POSITIVE LOGITS
    之一
    0.06
    мое
    0.06
    हिनी
    0.06
    跟大家
    0.06
     една
    0.06
     बुनियादी
    0.06
    给大家
    0.06
    밀
    0.06
     первых
    0.06
     publicado
    0.06
    Activations Density 0.021%

    No Known Activations