© 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. 118370
    Prev
    Next
    INDEX
    Explanations

    honesty or sincere

    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
     douceur
    -0.07
     authorship
    -0.07
     lids
    -0.07
    不
    -0.06
     নিজস্ব
    -0.06
    even
    -0.06
     yoktur
    -0.06
    ικοί
    -0.06
    ","/
    -0.06
    质
    -0.06
    POSITIVE LOGITS
     mushrooms
    0.06
    蝸
    0.06
     seemed
    0.06
     beurre
    0.06
     misguided
    0.06
     seems
    0.06
     ไง
    0.06
    で行
    0.06
     నిర్ణ
    0.06
     ईमान
    0.06
    Activations Density 0.005%

    No Known Activations