© 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. 119799
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     decreases
    -0.07
     can
    -0.06
     reliable
    -0.06
     ಕಡಿ
    -0.06
     mein
    -0.06
     instr
    -0.06
     reliant
    -0.06
     homegrown
    -0.06
    𖤐
    -0.06
     addictive
    -0.06
    POSITIVE LOGITS
    This
    0.07
     [
    0.07
    If
    0.07
     segue
    0.06
     which
    0.06
    Follow
    0.06
     slur
    0.06
    Over
    0.06
    这也
    0.06
     This
    0.06
    Activations Density 0.000%

    No Known Activations