© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118191
    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
     šest
    -0.08
     persönliche
    -0.07
     iniziale
    -0.07
    Individuals
    -0.07
     andere
    -0.07
     fotografía
    -0.07
     regalos
    -0.07
    ۶
    -0.06
    今年の
    -0.06
     där
    -0.06
    POSITIVE LOGITS
     granted
    0.05
     realistically
    0.05
     called
    0.05
    撇
    0.05
     normally
    0.05
    ‐
    0.05
    module
    0.05
     Ordin
    0.05
     Granted
    0.05
     называется
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.