© 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. 116740
    Prev
    Next
    INDEX
    Explanations

    CSS prefixes and specific attributes

    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
    チーム
    -0.07
    よい
    -0.06
    ("//
    -0.06
     τό
    -0.06
     waterfront
    -0.06
     گھ
    -0.06
    ですから
    -0.06
    对了
    -0.06
    ..."
    -0.05
    Moreover
    -0.05
    POSITIVE LOGITS
    花
    0.07
    with
    0.06
     magari
    0.06
     merasa
    0.06
     প্রবণ
    0.06
     με
    0.06
     formée
    0.06
     ব্য
    0.06
     Histogram
    0.06
     floral
    0.06
    Activations Density 0.001%

    No Known Activations