© 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. 120325
    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
    òria
    -0.06
     ἐν
    -0.06
    fand
    -0.05
     débit
    -0.05
     rhythmic
    -0.05
     affirming
    -0.05
     Baking
    -0.05
     către
    -0.05
     energ
    -0.05
     rozgry
    -0.05
    POSITIVE LOGITS
     gemeinsam
    0.07
     nawet
    0.06
    кування
    0.06
     deveria
    0.06
    還有
    0.06
    belong
    0.06
     irrepar
    0.06
     setiap
    0.06
     spared
    0.06
     공동
    0.06
    Activations Density 0.000%

    No Known Activations