© 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. 120523
    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
     വിവിധ
    -0.07
     他
    -0.06
     Πε
    -0.06
     regrett
    -0.06
     logrado
    -0.05
     தொகை
    -0.05
     ไหน
    -0.05
     апреле
    -0.05
     অথচ
    -0.05
     ezt
    -0.05
    POSITIVE LOGITS
    িয়ার
    0.06
     konfl
    0.06
     миру
    0.06
     Same
    0.06
     магнит
    0.06
     Hospitality
    0.06
    osaurus
    0.06
     функция
    0.06
    Ig
    0.06
     nước
    0.06
    Activations Density 0.000%

    No Known Activations