© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119687
    Prev
    Next
    INDEX
    Explanations

    board of directors

    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
     tienen
    -0.07
     Despite
    -0.06
     xix
    -0.06
     hacen
    -0.06
     قبل
    -0.06
    Despite
    -0.06
    ಧಿಕ
    -0.06
     رغم
    -0.06
     tiene
    -0.06
    !!!!
    -0.06
    POSITIVE LOGITS
     bardzo
    0.07
     не
    0.07
     очень
    0.07
     waktu
    0.07
     মাত্র
    0.06
     aonde
    0.06
     vastly
    0.06
     not
    0.06
     only
    0.06
     très
    0.06
    Activations Density 0.005%

    No Known Activations