© 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. 119303
    Prev
    Next
    INDEX
    Explanations

    section numbers

    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
     এসএম
    -0.07
     स्क्रीन
    -0.07
     اٹھ
    -0.07
    ैम
    -0.06
     hesit
    -0.06
     تغيير
    -0.06
     đọc
    -0.06
     have
    -0.06
     CHANGE
    -0.06
     อ่าน
    -0.06
    POSITIVE LOGITS
    ;
    0.07
    dis
    0.07
    ,
    0.06
    d
    0.06
    ata
    0.06
    💨
    0.06
    circa
    0.06
    তরে
    0.06
    Krist
    0.05
    asia
    0.05
    Activations Density 0.002%

    No Known Activations