© 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. 129351
    Prev
    Next
    INDEX
    Explanations

    Seinfeld

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    mostly
    -0.06
     some
    -0.06
     afore
    -0.06
    ophilia
    -0.06
    primarily
    -0.06
     Primarily
    -0.06
    Mostly
    -0.06
    Usually
    -0.06
     Usually
    -0.06
     mostly
    -0.05
    POSITIVE LOGITS
     يتم
    0.07
    ിക്ക
    0.06
     يت
    0.06
     tijd
    0.06
     الگ
    0.06
     seguidores
    0.06
     नाग
    0.06
    Alph
    0.06
     ينت
    0.06
     spécifiques
    0.06
    Activations Density 0.056%

    No Known Activations