© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118178
    Prev
    Next
    INDEX
    Explanations

    career before

    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
     และ
    -0.07
     minhas
    -0.06
     primeras
    -0.06
    我们的
    -0.06
     সবই
    -0.06
     Respuesta
    -0.06
    我們的
    -0.06
    ılara
    -0.06
     respuesta
    -0.06
     هذا
    -0.06
    POSITIVE LOGITS
     whereas
    0.07
     ALSO
    0.07
     cleverly
    0.06
     তৈরী
    0.06
    ),
    0.06
     loosened
    0.06
    !),
    0.06
    !.
    0.06
     convincingly
    0.06
     Whereas
    0.06
    Activations Density 0.002%

    No Known Activations