© 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. 120741
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
    Not in Any Lists

    No Comments

    Negative Logits
     dois
    -0.08
     два
    -0.07
     when
    -0.07
     two
    -0.07
    訢
    -0.06
     δύο
    -0.06
     etcétera
    -0.06
     nervoso
    -0.06
     когато
    -0.06
     dva
    -0.06
    POSITIVE LOGITS
    pheromone
    0.06
     मुख्यतः
    0.06
     soprattutto
    0.06
     که
    0.06
     prone
    0.06
     पटेल
    0.06
    彻底
    0.06
     различных
    0.06
     व्यवसा
    0.06
     семьи
    0.06
    Activations Density 0.002%

    No Known Activations