© 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. 128275
    Prev
    Next
    INDEX
    Explanations

    reserved. rights

    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
     evidently
    -0.06
    변경
    -0.06
     जीवन
    -0.06
     حزب
    -0.06
     extensive
    -0.05
     you
    -0.05
     دوسرے
    -0.05
    phot
    -0.05
     ఎంత
    -0.05
     오늘은
    -0.05
    POSITIVE LOGITS
     trong
    0.08
     في
    0.08
    achricht
    0.07
     în
    0.07
     জলাবদ্ধ
    0.06
    म्ब
    0.06
     в
    0.06
    在
    0.06
    astres
    0.06
    मे
    0.06
    Activations Density 0.003%

    No Known Activations