© 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. 128674
    Prev
    Next
    INDEX
    Explanations

    key-value pairs with "name"

    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
     потенциа
    -0.06
    1
    -0.06
     unterschied
    -0.06
    थियों
    -0.06
     будет
    -0.06
     Unterschied
    -0.06
     +
    -0.06
     ihres
    -0.06
     perbedaan
    -0.05
     их
    -0.05
    POSITIVE LOGITS
     albums
    0.07
    quick
    0.06
    మ
    0.06
     Britannica
    0.06
     WorldCat
    0.06
     millas
    0.05
     Awards
    0.05
    终止
    0.05
     Ingl
    0.05
    Albums
    0.05
    Activations Density 0.002%

    No Known Activations