© 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. 120961
    Prev
    Next
    INDEX
    Explanations

    vitamin b deficiency, blindness, supplementation

    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
     دانشگاه
    -0.07
     Bowen
    -0.07
    それ
    -0.07
     ராம
    -0.07
     важли
    -0.06
     Citrus
    -0.06
     adoles
    -0.06
     depende
    -0.06
     importantes
    -0.06
     yu
    -0.06
    POSITIVE LOGITS
    نین
    0.05
    guide
    0.05
     one
    0.05
     alight
    0.05
     ”
    0.05
     astray
    0.05
    sendLog
    0.05
     जागर
    0.05
     स्टेशनों
    0.05
    xlink
    0.05
    Activations Density 0.047%

    No Known Activations