© 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. 121006
    Prev
    Next
    INDEX
    Explanations

    services and digital

    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
     엄청
    -0.08
    ᥱ
    -0.07
     několik
    -0.07
     굉장
    -0.07
     خیلی
    -0.06
     серьез
    -0.06
     ปลา
    -0.06
    皆さん
    -0.06
     says
    -0.06
    です
    -0.06
    POSITIVE LOGITS
     these
    0.08
     the
    0.06
     thèse
    0.06
     जो
    0.06
     এবং
    0.06
     dalam
    0.06
     الهند
    0.06
    <eos>
    0.06
    வற்ற
    0.05
     When
    0.05
    Activations Density 0.107%

    No Known Activations