© 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. 128226
    Prev
    Next
    INDEX
    Explanations

    forward declaration

    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
     آغاز
    -0.06
    numerator
    -0.06
     berangkat
    -0.06
     Além
    -0.06
    Makefile
    -0.06
    GONE
    -0.06
     кеңсеси
    -0.06
     olacaktır
    -0.06
     arbej
    -0.06
    息子
    -0.06
    POSITIVE LOGITS
     नितिन
    0.06
    指定的
    0.06
     cutting
    0.06
     technological
    0.06
    english
    0.05
    otec
    0.05
     Geg
    0.05
     précisément
    0.05
    dark
    0.05
     black
    0.05
    Activations Density 0.001%

    No Known Activations