© 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. 116573
    Prev
    Next
    INDEX
    Explanations

    medical study descriptions

    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
     as
    -0.08
     gives
    -0.08
     taff
    -0.07
     Gives
    -0.07
     it
    -0.06
     at
    -0.06
     makes
    -0.06
     Carefully
    -0.06
     this
    -0.06
    忘了
    -0.06
    POSITIVE LOGITS
     entrambi
    0.07
    どちら
    0.06
     keiner
    0.06
     entrambe
    0.06
    Individual
    0.06
    PhysRev
    0.06
     symmetrical
    0.06
    穏
    0.06
    för
    0.06
    ពួក
    0.06
    Activations Density 0.012%

    No Known Activations