© 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. 120984
    Prev
    Next
    INDEX
    Explanations

    to + verb

    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
     orient
    -0.06
    ږد
    -0.06
     कोऑ
    -0.06
     क्वांटिटी
    -0.06
    along
    -0.06
                
    -0.06
     motifs
    -0.06
     centering
    -0.06
     মূলত
    -0.06
     தொடங்கி
    -0.06
    POSITIVE LOGITS
     کپ
    0.06
     indústria
    0.06
     شركات
    0.06
     новой
    0.06
     realice
    0.06
     शही
    0.06
     верши
    0.06
     factories
    0.06
    所以在
    0.06
     tarda
    0.05
    Activations Density 0.014%

    No Known Activations