© 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. 119442
    Prev
    Next
    INDEX
    Explanations

    code parsing or foreign language keywords

    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
     posibles
    -0.08
     possibili
    -0.08
     यथा
    -0.07
     ใช้
    -0.07
     mogelijk
    -0.07
     possible
    -0.06
     وتن
    -0.06
    橫
    -0.06
     setiap
    -0.06
     youthful
    -0.06
    POSITIVE LOGITS
     trivially
    0.07
     hyperlink
    0.06
     comparable
    0.06
     identically
    0.06
     добре
    0.06
    Clazz
    0.06
    男人
    0.06
     bijective
    0.06
    Similarly
    0.06
     erwäh
    0.06
    Activations Density 0.003%

    No Known Activations