© 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. 115945
    Prev
    Next
    INDEX
    Explanations

    reporting verbs followed by "that"

    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
     están
    -0.07
     более
    -0.07
     především
    -0.07
     കൂടുതല്‍
    -0.07
    धिक
    -0.07
     bardziej
    -0.06
     aa
    -0.06
     것은
    -0.06
     nhưng
    -0.06
     უფრო
    -0.06
    POSITIVE LOGITS
    There
    0.06
    keys
    0.06
     halfway
    0.06
     recent
    0.06
     大
    0.06
     মাঝে
    0.06
    近年
    0.06
     There
    0.06
     有
    0.06
                                
    0.05
    Activations Density 0.003%

    No Known Activations