© 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. 129659
    Prev
    Next
    INDEX
    Explanations

    tennis and happiness

    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
     could
    -0.06
     rubric
    -0.06
    could
    -0.06
    Could
    -0.06
     czerw
    -0.06
     prenn
    -0.06
    从业
    -0.06
     कोश
    -0.05
    phases
    -0.05
     może
    -0.05
    POSITIVE LOGITS
    を楽し
    0.07
    欢乐
    0.06
    🎾
    0.06
    campfire
    0.06
    阳光
    0.06
    ysi
    0.06
     ক্রেডিট
    0.06
     Happiness
    0.06
     والتي
    0.06
    乐观
    0.06
    Activations Density 0.005%

    No Known Activations