© 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. 129599
    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
     to
    -0.06
    /
    -0.06
     आयुर्वे
    -0.05
    ಟ
    -0.05
     without
    -0.05
     well
    -0.05
     str
    -0.05
     জঙ্গি
    -0.05
     meticulously
    -0.05
    ped
    -0.05
    POSITIVE LOGITS
    Other
    0.08
     diğer
    0.07
     другие
    0.07
     actresses
    0.07
     دیگر
    0.07
     टेस्ट
    0.07
     ఇతర
    0.06
     سایر
    0.06
    other
    0.06
    people
    0.06
    Activations Density 0.000%

    No Known Activations