© 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. 116514
    Prev
    Next
    INDEX
    Explanations

    closing files or code blocks

    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
     deberán
    -0.06
    都合
    -0.06
    also
    -0.06
     ràng
    -0.06
     DRM
    -0.06
     점점
    -0.06
     poderia
    -0.06
    állítás
    -0.06
     city
    -0.06
     거기에
    -0.06
    POSITIVE LOGITS
     during
    0.06
     projectile
    0.06
     নিয়ন্ত্রণে
    0.05
     Async
    0.05
    Async
    0.05
     participantes
    0.05
     rouges
    0.05
     Podcast
    0.05
    ुरी
    0.05
     Aster
    0.05
    Activations Density 0.002%

    No Known Activations