© 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. 119679
    Prev
    Next
    INDEX
    Explanations

    stats or counts

    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
     hicieron
    -0.07
     сделали
    -0.07
    过去的
    -0.07
     to
    -0.07
     hizo
    -0.07
     قدیمی
    -0.06
     식품
    -0.06
     делает
    -0.06
     некоторых
    -0.06
    ྷ
    -0.06
    POSITIVE LOGITS
     Barack
    0.06
     distinctly
    0.05
    odhya
    0.05
    b
    0.05
    zyb
    0.05
    ianic
    0.05
    쭉
    0.05
     apartheid
    0.05
     特
    0.05
     父
    0.05
    Activations Density 0.001%

    No Known Activations