© 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. 116044
    Prev
    Next
    INDEX
    Explanations

    verbs related to listing or categories

    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
     notificación
    -0.06
     gingen
    -0.06
     standardised
    -0.06
     notification
    -0.06
     strapping
    -0.05
     respective
    -0.05
    ပျ
    -0.05
    ပြန်
    -0.05
     Early
    -0.05
     imparted
    -0.05
    POSITIVE LOGITS
     garanti
    0.07
    这样
    0.07
    ゆっくり
    0.06
    お店
    0.06
    ड़ी
    0.06
    這樣
    0.06
    minimum
    0.06
     최소
    0.06
     such
    0.06
     Empor
    0.06
    Activations Density 0.001%

    No Known Activations