© 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. 119865
    Prev
    Next
    INDEX
    Explanations

    html title tag

    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
     изменить
    -0.07
     ändern
    -0.06
    措施
    -0.06
     包括
    -0.06
    或者
    -0.06
     mudar
    -0.06
     ঘিরে
    -0.06
     என்னும்
    -0.06
     incluindo
    -0.06
     affiliation
    -0.06
    POSITIVE LOGITS
     consequently
    0.07
     इन
    0.06
     main
    0.06
    alice
    0.06
     of
    0.06
     Aside
    0.06
    micron
    0.06
     Furthermore
    0.06
     on
    0.06
     ইংল্যান্ড
    0.06
    Activations Density 0.001%

    No Known Activations