© 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. 118169
    Prev
    Next
    INDEX
    Explanations

    body weight and mass

    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
     இருந்தால்
    -0.07
    サイズの
    -0.07
     sized
    -0.07
    をお願い
    -0.07
     εργ
    -0.06
     অথবা
    -0.06
     आवश्यक
    -0.06
     recommendations
    -0.06
     শারীরিক
    -0.06
    샀
    -0.06
    POSITIVE LOGITS
     supposedly
    0.06
    late
    0.06
     potent
    0.06
    時点
    0.06
     hệ
    0.06
    ตอน
    0.06
    当時
    0.06
     many
    0.06
    当时
    0.06
     अध्या
    0.05
    Activations Density 0.002%

    No Known Activations