© 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. 116040
    Prev
    Next
    INDEX
    Explanations

    skin and hair care hydration

    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
     প্রভাব
    -0.06
    効果
    -0.06
     ONLY
    -0.06
    功效
    -0.06
    Methoxy
    -0.06
     etkisi
    -0.06
     либо
    -0.06
     Kenneth
    -0.06
    艨
    -0.06
     apenas
    -0.06
    POSITIVE LOGITS
    land
    0.07
    現在の
    0.06
    脱
    0.06
     plight
    0.06
     compassion
    0.06
    Winter
    0.06
     SPDX
    0.06
     condiciones
    0.06
    mailto
    0.06
     extensible
    0.06
    Activations Density 0.008%

    No Known Activations