© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130187
    Prev
    Next
    INDEX
    Explanations

    html input/select attributes

    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
     способности
    -0.06
    彧
    -0.06
     tensile
    -0.06
    ♒
    -0.06
    สถานที่
    -0.06
    oseconds
    -0.06
    场所
    -0.06
    श्यक
    -0.06
    喋
    -0.06
     dangerous
    -0.06
    POSITIVE LOGITS
     nowadays
    0.06
     despite
    0.06
                                
    0.06
     (
    0.06
     ಈಗ
    0.06
     spanning
    0.06
    bien
    0.06
    liceerd
    0.06
    *(
    0.05
     histori
    0.05
    Activations Density 0.004%

    No Known Activations