© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119223
    Prev
    Next
    INDEX
    Explanations

    `block` or `trans` followed by `{%` or `html` tags

    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
     নিমিত
    -0.06
     manned
    -0.06
     أبريل
    -0.06
     automation
    -0.06
     wildlife
    -0.06
     herbaceous
    -0.06
     mammalian
    -0.06
    estab
    -0.06
     पूछताछ
    -0.06
    predictions
    -0.06
    POSITIVE LOGITS
    이나
    0.07
    Comparing
    0.07
     особли
    0.07
     Comparing
    0.06
     bastante
    0.06
     дополни
    0.06
    內的
    0.06
     workman
    0.06
    धील
    0.06
    antin
    0.06
    Activations Density 0.001%

    No Known Activations