© 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. 120743
    Prev
    Next
    INDEX
    Explanations

    simulator, code, model, method

    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
     analysis
    -0.06
     ઓ
    -0.06
     preview
    -0.06
     مشینیں
    -0.06
     requisite
    -0.06
     doświad
    -0.06
    需要的
    -0.06
     recommended
    -0.06
     ப்
    -0.06
    仕上げ
    -0.06
    POSITIVE LOGITS
     circulatory
    0.06
     também
    0.06
     때문에
    0.06
     also
    0.06
     деятельность
    0.06
     सीताराम
    0.06
    بت
    0.06
     జాగ
    0.06
     sometime
    0.05
     ambil
    0.05
    Activations Density 0.013%

    No Known Activations