© 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. 117524
    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
     performance
    -0.07
    performance
    -0.06
    ítmény
    -0.06
     colectivo
    -0.06
     garante
    -0.06
     Performance
    -0.06
    Performance
    -0.05
     TIR
    -0.05
    Park
    -0.05
     transforma
    -0.05
    POSITIVE LOGITS
     what
    0.07
     podpis
    0.07
     jenis
    0.06
     Within
    0.06
     múlti
    0.06
     إِن
    0.06
     savers
    0.06
    考え
    0.06
     furthermore
    0.06
    Within
    0.06
    Activations Density 0.000%

    No Known Activations