© 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. 121040
    Prev
    Next
    INDEX
    Explanations

    for or in

    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
     the
    -0.06
     consequences
    -0.06
    fY
    -0.06
     biais
    -0.06
     ONLY
    -0.06
     NEVER
    -0.06
     HAVE
    -0.06
    getenv
    -0.06
     MUST
    -0.05
     Have
    -0.05
    POSITIVE LOGITS
     tantas
    0.06
     posthum
    0.06
     cualquiera
    0.06
     ఎక్కువ
    0.06
     เด้อ
    0.06
     άλλ
    0.06
     دیگر
    0.06
     livestream
    0.05
    more
    0.05
     Bás
    0.05
    Activations Density 0.014%

    No Known Activations