© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120724
    Prev
    Next
    INDEX
    Explanations

    77Se NMR

    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
     மற்றொரு
    -0.06
     iteratively
    -0.06
     repeated
    -0.06
     जहां
    -0.05
     vastu
    -0.05
     चुक
    -0.05
    ponen
    -0.05
    ैर्य
    -0.05
    在哪里
    -0.05
     accessing
    -0.05
    POSITIVE LOGITS
    現場
    0.07
     …….
    0.06
    判断
    0.06
     ……..
    0.06
    口罩
    0.06
    으로
    0.06
     XXL
    0.06
    Rain
    0.06
     সর্বপ্রথম
    0.06
    نج
    0.06
    Activations Density 0.001%

    No Known Activations