© 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. 128270
    Prev
    Next
    INDEX
    Explanations

    If you don't

    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
     give
    -0.07
    gives
    -0.06
    checks
    -0.06
    را
    -0.06
     allows
    -0.06
    以免
    -0.06
    These
    -0.06
    这么多
    -0.06
     grievance
    -0.06
     كلها
    -0.06
    POSITIVE LOGITS
     your
    0.07
     recently
    0.07
     recientemente
    0.06
    最近
    0.06
     recent
    0.06
     recentemente
    0.06
    ̒
    0.06
    ர்த
    0.06
     koh
    0.06
     bislang
    0.06
    Activations Density 0.006%

    No Known Activations