© 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. 129358
    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
     constantemente
    -0.07
     uniquement
    -0.07
     mantenimiento
    -0.06
     nabíz
    -0.06
     proposé
    -0.06
     stets
    -0.06
     కే
    -0.06
    mainly
    -0.06
    untuk
    -0.06
     বোঝার
    -0.06
    POSITIVE LOGITS
     even
    0.06
     পুর্ব
    0.06
     intentional
    0.06
     will
    0.06
     또
    0.06
     sogar
    0.06
     트리플
    0.05
    蓋
    0.05
     Some
    0.05
     Even
    0.05
    Activations Density 0.000%

    No Known Activations