© 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. 119964
    Prev
    Next
    INDEX
    Explanations

    same [category] followed by descriptive details

    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
     دوم
    -0.06
     incluido
    -0.06
     atau
    -0.06
     first
    -0.05
     conhe
    -0.05
     erinnert
    -0.05
    ുകൂ
    -0.05
     remnant
    -0.05
    が変わ
    -0.05
     omitted
    -0.05
    POSITIVE LOGITS
     crafted
    0.06
     decât
    0.06
     Sekunden
    0.06
    নির্দিষ্ট
    0.06
     few
    0.06
    ાઇ
    0.06
     regarding
    0.06
    보다는
    0.06
     Sleeping
    0.06
     बढ़ाने
    0.06
    Activations Density 0.024%

    No Known Activations