© 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. 129283
    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
    Italie
    -0.06
    obligation
    -0.06
    などは
    -0.06
     secreto
    -0.06
     cependant
    -0.06
    <0xEF>
    -0.06
     puntual
    -0.06
     Vinc
    -0.06
     diantaranya
    -0.06
    ConvertTo
    -0.06
    POSITIVE LOGITS
     andere
    0.09
     other
    0.08
     остальные
    0.08
     другие
    0.07
     Other
    0.07
     diğer
    0.07
    Other
    0.07
    OTHER
    0.07
     anderen
    0.06
     demás
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.