© 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. 116186
    Prev
    Next
    INDEX
    Explanations

    primary server member

    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
     효율
    -0.07
    Siehe
    -0.07
     দুজন
    -0.07
     έχουν
    -0.07
     remoto
    -0.06
     vastu
    -0.06
     számos
    -0.06
     efficiently
    -0.06
     существу
    -0.06
     auf
    -0.06
    POSITIVE LOGITS
    warning
    0.07
     ratepayers
    0.06
    code
    0.06
     তির
    0.06
    plash
    0.06
     describing
    0.06
     Symbolic
    0.05
    レルギー
    0.05
    近年来
    0.05
    ウェット
    0.05
    Activations Density 0.001%

    No Known Activations