© 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. 130525
    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
     повлия
    -0.06
    િસ્
    -0.06
    état
    -0.06
     aesthetically
    -0.06
     extremely
    -0.06
    тических
    -0.06
    しますが
    -0.06
     टेक्
    -0.06
     keadaan
    -0.06
     സൂ
    -0.06
    POSITIVE LOGITS
     such
    0.06
     服务
    0.06
     welcome
    0.05
     слово
    0.05
    Such
    0.05
     ­
    0.05
     সিংহ
    0.05
    ¬
    0.05
     परिचित
    0.05
    დის
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.