© 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. 116130
    Prev
    Next
    INDEX
    Explanations

    the future

    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
     ইংরেজ
    -0.06
     Aufbau
    -0.05
     NATIONAL
    -0.05
    간
    -0.05
     such
    -0.05
     for
    -0.05
    ետ
    -0.05
     inflam
    -0.05
    建立
    -0.05
     also
    -0.05
    POSITIVE LOGITS
     толькі
    0.07
     பயன்படுத்த
    0.07
     tikai
    0.06
     svaki
    0.06
     только
    0.06
    monthly
    0.06
     படத்தை
    0.06
    minas
    0.06
     каждую
    0.06
     tìm
    0.06
    Activations Density 0.001%

    No Known Activations