© 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. 118204
    Prev
    Next
    INDEX
    Explanations

    Classpath exception

    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
     thousands
    -0.06
     hundreds
    -0.06
     akár
    -0.06
    以
    -0.05
    ವರೆಗೆ
    -0.05
     an
    -0.05
     Validation
    -0.05
     Gewicht
    -0.05
     jederzeit
    -0.05
    >>>>
    -0.05
    POSITIVE LOGITS
     লক
    0.07
     zicht
    0.07
     وضع
    0.06
     област
    0.06
     कार्यक्रम
    0.06
     طبعا
    0.06
     abbastanza
    0.06
     Mainly
    0.06
     பசு
    0.06
     shorth
    0.06
    Activations Density 0.001%

    No Known Activations