© 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. 130062
    Prev
    Next
    INDEX
    Explanations

    first inning

    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
     confirmar
    -0.06
    เพิ่มเติม
    -0.06
    变更
    -0.06
     confirmer
    -0.06
     masih
    -0.06
    再度
    -0.06
    ㄴ
    -0.06
     confirm
    -0.06
     exhausted
    -0.06
     weiterhin
    -0.06
    POSITIVE LOGITS
     initialization
    0.07
     Initialization
    0.07
     initializing
    0.07
     scoreless
    0.06
    这种
    0.06
    initial
    0.06
     initial
    0.06
     takiego
    0.06
     entire
    0.06
     такого
    0.06
    Activations Density 0.017%

    No Known Activations