© 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. 127972
    Prev
    Next
    INDEX
    Explanations

    mathematical terms (exponents, variables)

    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
    뮐
    -0.06
    银行
    -0.06
    McL
    -0.06
     अमेजन
    -0.06
    entrop
    -0.06
     Internation
    -0.06
     حقیقی
    -0.06
     बैंकिंग
    -0.06
     ବି
    -0.06
    ന്നെ
    -0.06
    POSITIVE LOGITS
    ,
    0.07
    .
    0.06
     Tec
    0.06
    、
    0.06
     taxonomy
    0.06
     nombreux
    0.05
     pleinement
    0.05
     actually
    0.05
     S
    0.05
     évidemment
    0.05
    Activations Density 0.001%

    No Known Activations