© 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. 120868
    Prev
    Next
    INDEX
    Explanations

    date review/rating

    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
     যান
    -0.06
     već
    -0.06
     circonst
    -0.06
    既に
    -0.06
     already
    -0.06
    ;
    -0.06
    Already
    -0.06
     δια
    -0.05
     postings
    -0.05
    全部
    -0.05
    POSITIVE LOGITS
     আস্থা
    0.06
     pled
    0.06
     would
    0.06
    鸴
    0.06
     what
    0.06
    hci
    0.06
     aici
    0.06
     नामक
    0.06
     gelungen
    0.06
    pictured
    0.06
    Activations Density 0.010%

    No Known Activations