© 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. 120875
    Prev
    Next
    INDEX
    Explanations

    locations and travel descriptions

    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
     создать
    -0.06
     initiative
    -0.06
     शुरु
    -0.06
     ontstaan
    -0.06
     specjal
    -0.06
     kok
    -0.05
     criticism
    -0.05
     inoc
    -0.05
     menjaga
    -0.05
    apopt
    -0.05
    POSITIVE LOGITS
     reveals
    0.09
     visited
    0.07
     visiter
    0.07
    ował
    0.07
     visitare
    0.07
     revealing
    0.07
     besuchte
    0.07
     threw
    0.07
     revela
    0.07
     révèle
    0.07
    Activations Density 0.006%

    No Known Activations