© 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. 129383
    Prev
    Next
    INDEX
    Explanations

    sphincter LES tonus urogenital muscle imaging

    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
    佹
    -0.07
     άλλ
    -0.07
    江苏
    -0.06
    꽂
    -0.06
     paix
    -0.06
     cuidadosamente
    -0.06
    為什麼
    -0.06
     maximale
    -0.06
    Leadership
    -0.06
     on
    -0.06
    POSITIVE LOGITS
     would
    0.06
    Worldwide
    0.06
     these
    0.06
     foro
    0.06
    ளிட
    0.06
     trainable
    0.06
     pelvic
    0.06
     Pilates
    0.05
    cult
    0.05
    training
    0.05
    Activations Density 0.002%

    No Known Activations