© 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. 130126
    Prev
    Next
    INDEX
    Explanations

    `.`, `Q`, or `Na` followed by code/text

    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
     these
    -0.08
     not
    -0.07
     sharing
    -0.07
     this
    -0.06
     этих
    -0.06
     dieser
    -0.06
     Not
    -0.06
     này
    -0.06
     powinien
    -0.06
    示例
    -0.06
    POSITIVE LOGITS
     مُعرِّف
    0.06
     fanno
    0.06
     अक्सर
    0.06
     ਵਿ
    0.06
     ব্যবহার
    0.06
    良く
    0.06
     często
    0.06
     constitue
    0.06
     کان
    0.06
     Things
    0.06
    Activations Density 0.002%

    No Known Activations