© 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. 120992
    Prev
    Next
    INDEX
    Explanations

    protein, percentage, ratio, Array, relative, examiner

    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
    Negative Logits
     by
    -0.08
     चार
    -0.06
    의
    -0.06
     ನ್ಯಾಯ
    -0.06
     including
    -0.06
    ARRAY
    -0.06
     risultato
    -0.06
    hereafter
    -0.06
     ব্যতীত
    -0.06
    hence
    -0.06
    POSITIVE LOGITS
     dziś
    0.06
     ///
    0.06
     বছরে
    0.06
    atini
    0.06
    თან
    0.06
    แต่
    0.06
     zna
    0.06
     మారింది
    0.06
    지만
    0.06
     なん
    0.06
    Activations Density 0.004%

    No Known Activations