© 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. 116619
    Prev
    Next
    INDEX
    Explanations

    code syntax and symbols

    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
     overall
    -0.06
     at
    -0.06
     on
    -0.06
     other
    -0.06
     على
    -0.06
     προς
    -0.06
     herhangi
    -0.06
     σε
    -0.06
     Birk
    -0.06
    如果您
    -0.05
    POSITIVE LOGITS
     righteous
    0.07
     toug
    0.07
     ஒவ்வொரு
    0.07
     because
    0.06
     juga
    0.06
    挖
    0.06
    스는
    0.06
    だけでなく
    0.06
    每
    0.06
     giv
    0.06
    Activations Density 0.003%

    No Known Activations