© 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. 129469
    Prev
    Next
    INDEX
    Explanations

    keywords, types, and foreign words

    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
     defying
    -0.06
     versus
    -0.06
     क्यों
    -0.06
     ∼
    -0.05
     why
    -0.05
     domani
    -0.05
     about
    -0.05
     vs
    -0.05
    yno
    -0.05
     
    -0.05
    POSITIVE LOGITS
     કહ્યું
    0.06
     nuestras
    0.06
     有
    0.06
    我们的
    0.06
     Tidak
    0.06
     Lebensmittel
    0.06
    サービス
    0.06
     tidak
    0.06
    ன்மைய
    0.06
    我們的
    0.06
    Activations Density 0.010%

    No Known Activations