© 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. 128088
    Prev
    Next
    INDEX
    Explanations

    regulation of biological processes

    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
     strangely
    -0.07
     стран
    -0.06
     oddly
    -0.06
    一個
    -0.06
    surgical
    -0.06
     how
    -0.06
    ล็อก
    -0.06
     arreg
    -0.06
    如何
    -0.06
     ১৯
    -0.06
    POSITIVE LOGITS
     якщо
    0.07
     tovább
    0.06
     continues
    0.06
     pathways
    0.06
     স্বভাব
    0.06
     વર્ષ
    0.06
     info
    0.06
     devam
    0.06
     няко
    0.06
     зазна
    0.06
    Activations Density 0.004%

    No Known Activations