© 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. 127936
    Prev
    Next
    INDEX
    Explanations

    introduction or section headers

    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
     mencionados
    -0.06
     involve
    -0.06
    asso
    -0.06
     other
    -0.06
    ,
    -0.06
    各种
    -0.06
     innych
    -0.06
     інших
    -0.06
     referenced
    -0.06
     thời
    -0.06
    POSITIVE LOGITS
    >{</
    0.06
     sudoku
    0.06
     repack
    0.06
     সমাবে
    0.06
     rugged
    0.06
    IRCON
    0.06
     LEARN
    0.06
     COPY
    0.06
    ্বক
    0.05
    Region
    0.05
    Activations Density 0.001%

    No Known Activations