© 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. 128807
    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
    스러운
    -0.06
    ojana
    -0.06
     it
    -0.06
    एक
    -0.06
    を使って
    -0.06
     Burnley
    -0.06
     wszyst
    -0.06
    に限
    -0.06
     secteur
    -0.06
    vegan
    -0.06
    POSITIVE LOGITS
    继续
    0.08
    繼續
    0.07
     continue
    0.07
    छि
    0.07
     weiter
    0.06
     continuar
    0.06
    ீஸ்
    0.06
     continuing
    0.06
    ...');
    0.06
    continue
    0.06
    Activations Density 0.000%

    No Known Activations