© 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. 128068
    Prev
    Next
    INDEX
    Explanations

    coding, utf-8

    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
     менедж
    -0.06
    yesters
    -0.06
     sogar
    -0.06
    Wra
    -0.06
     nawet
    -0.06
     তাঁদের
    -0.06
     vetted
    -0.06
    Management
    -0.06
    itej
    -0.06
    wrap
    -0.06
    POSITIVE LOGITS
    тного
    0.06
     మరో
    0.06
     todavía
    0.06
     скорее
    0.06
    祭り
    0.06
    －
    0.06
    最終
    0.06
     해야
    0.06
     wahrscheinlich
    0.06
     engineering
    0.06
    Activations Density 0.003%

    No Known Activations