© 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. 119014
    Prev
    Next
    INDEX
    Explanations

    eval, reflection, forName

    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
    istán
    -0.07
     prepara
    -0.06
     preparation
    -0.06
     끊
    -0.06
     together
    -0.06
    伫
    -0.06
    끊
    -0.06
     modeling
    -0.06
     preparación
    -0.06
    ŵ
    -0.06
    POSITIVE LOGITS
     धर्मेंद्र
    0.06
     கொஞ்சம்
    0.06
     prank
    0.06
    中古
    0.06
     TOOL
    0.05
     mischievous
    0.05
     leggera
    0.05
     Reset
    0.05
     ঘুষ
    0.05
     hilarious
    0.05
    Activations Density 0.010%

    No Known Activations