© 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. 128162
    Prev
    Next
    INDEX
    Explanations

    liquid crystal between

    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
    ερμαν
    -0.07
    囂
    -0.06
     noise
    -0.06
     monopolies
    -0.06
     Apple
    -0.06
     कसे
    -0.06
     نمایش
    -0.06
     நில
    -0.06
     Noise
    -0.06
    нер
    -0.06
    POSITIVE LOGITS
     between
    0.07
     між
    0.07
    Between
    0.07
     između
    0.06
     между
    0.06
    Positive
    0.06
    まさに
    0.06
     olho
    0.06
     именно
    0.06
     FTA
    0.06
    Activations Density 0.004%

    No Known Activations