© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118309
    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
     ln
    -0.06
    ása
    -0.06
    idence
    -0.06
    ccncc
    -0.06
     building
    -0.06
     trei
    -0.06
     trzech
    -0.06
     menciptakan
    -0.06
    Guests
    -0.06
     ases
    -0.06
    POSITIVE LOGITS
     some
    0.07
     कुछ
    0.07
    some
    0.06
    บาง
    0.06
    ewhat
    0.06
    Some
    0.06
     برخی
    0.06
    what
    0.06
    कुछ
    0.06
     terbesar
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.