© 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. 119779
    Prev
    Next
    INDEX
    Explanations

    code, documentation headers, and tags

    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
     ইচ্ছ
    -0.06
     impr
    -0.06
     సీ
    -0.05
    Java
    -0.05
     sku
    -0.05
    ழக
    -0.05
    sid
    -0.05
    Song
    -0.05
     Java
    -0.05
    自己
    -0.05
    POSITIVE LOGITS
    のような
    0.07
     Superstar
    0.06
    வின்
    0.06
     deren
    0.06
     เช่น
    0.06
     मोट
    0.06
     pessoas
    0.06
     ಏನು
    0.06
     such
    0.06
     الحاج
    0.06
    Activations Density 0.001%

    No Known Activations