© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116189
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and types

    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
     완전히
    -0.07
     constamment
    -0.07
    完全に
    -0.07
    pletely
    -0.06
     постоянно
    -0.06
    Buffalo
    -0.06
     बुरे
    -0.06
     Trials
    -0.06
     complètement
    -0.06
    常に
    -0.06
    POSITIVE LOGITS
     veranda
    0.06
    vtk
    0.06
     resulting
    0.06
     sculptural
    0.06
     Pythag
    0.06
    の名前
    0.05
     securing
    0.05
    ））
    0.05
     clima
    0.05
     via
    0.05
    Activations Density 0.001%

    No Known Activations