© 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. 116263
    Prev
    Next
    INDEX
    Explanations

    leaving or staying decisions

    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
     pojawi
    -0.07
     Taipei
    -0.06
     requisite
    -0.06
     اسرائی
    -0.06
     तत्
    -0.06
     tyto
    -0.06
     на
    -0.06
     Ihr
    -0.06
    が登場
    -0.06
    appears
    -0.06
    POSITIVE LOGITS
     relationships
    0.07
     friendship
    0.07
     เขา
    0.07
     loyalty
    0.07
     his
    0.06
     উদ্দেশ্য
    0.06
    乖
    0.06
    🐍
    0.06
    変動
    0.06
    他的
    0.06
    Activations Density 0.035%

    No Known Activations