© 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. 116965
    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
    recognition
    -0.06
    Recogn
    -0.06
    uelles
    -0.06
     lately
    -0.06
     ventric
    -0.06
     eukaryotic
    -0.06
    शूट
    -0.06
     paddy
    -0.06
     polygons
    -0.06
     exceptionally
    -0.06
    POSITIVE LOGITS
     basicamente
    0.06
    বাচক
    0.06
    attributes
    0.06
     مجموعة
    0.06
     संगीत
    0.06
     боюнча
    0.06
    attribute
    0.06
     básicamente
    0.06
     কোথা
    0.06
     Additionally
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.