© 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. 119460
    Prev
    Next
    INDEX
    Explanations

    mathematical questions about functions

    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
     Sweden
    -0.06
     antisemit
    -0.06
     مدار
    -0.06
    😆
    -0.06
     ›
    -0.06
    ___
    -0.05
     lcm
    -0.05
     aching
    -0.05
     Ezra
    -0.05
    ~~
    -0.05
    POSITIVE LOGITS
     разгово
    0.07
    measured
    0.07
    اهرين
    0.06
     rapor
    0.06
    சிவ
    0.06
     स्प्रे
    0.06
     কিছুক্ষণ
    0.06
    哭
    0.06
     पुन्हा
    0.06
    lige
    0.06
    Activations Density 0.001%

    No Known Activations