© 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. 117368
    Prev
    Next
    INDEX
    Explanations

    General information

    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
     nuestro
    -0.07
     nosso
    -0.07
     nossos
    -0.07
     unseren
    -0.07
     naszych
    -0.07
     ನಮ್ಮ
    -0.06
     csak
    -0.06
     कारगर
    -0.06
     다양한
    -0.06
     हमारे
    -0.06
    POSITIVE LOGITS
     also
    0.08
     still
    0.07
     sekaligus
    0.06
    KU
    0.06
    still
    0.06
     vielä
    0.06
     উপন্যাস
    0.06
    ล็อต
    0.06
    гут
    0.06
     zároveň
    0.06
    Activations Density 0.004%

    No Known Activations