© 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. 129398
    Prev
    Next
    INDEX
    Explanations

    code/file names followed by punctuation

    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
     which
    -0.10
     کدام
    -0.07
    which
    -0.07
    XIII
    -0.06
     or
    -0.06
     ซึ่ง
    -0.06
     hopefully
    -0.06
    もしくは
    -0.06
     an
    -0.06
    ซึ่ง
    -0.06
    POSITIVE LOGITS
    :
    0.07
    醌
    0.06
     până
    0.05
     உலகில்
    0.05
     ముందు
    0.05
     dacă
    0.05
    前
    0.05
     растений
    0.05
     límite
    0.05
    années
    0.05
    Activations Density 0.005%

    No Known Activations