© 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. 119766
    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
    Sydney
    -0.07
     Bondi
    -0.06
    FY
    -0.06
     Jammu
    -0.06
     semble
    -0.06
     bestätigt
    -0.06
    确认
    -0.06
    英文
    -0.06
     saloon
    -0.06
     conformations
    -0.05
    POSITIVE LOGITS
     portrays
    0.06
     deficient
    0.06
     zudem
    0.06
    琛
    0.06
     passionately
    0.06
     뿐
    0.06
     სახელმწიფ
    0.06
    ﻨ
    0.06
     súčas
    0.06
     loss
    0.06
    Activations Density 0.000%

    No Known Activations