© 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. 119683
    Prev
    Next
    INDEX
    Explanations

    conditional else if

    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
     आउट
    -0.06
     asserting
    -0.06
    မှု
    -0.06
     three
    -0.06
     comentado
    -0.06
     принятия
    -0.06
     एट
    -0.06
    shoe
    -0.05
     ③
    -0.05
     Patel
    -0.05
    POSITIVE LOGITS
     решили
    0.07
    都已经
    0.06
    которы
    0.06
    Otra
    0.06
     करवाया
    0.06
    urahan
    0.06
     कामकाजी
    0.06
     cercano
    0.06
     সরে
    0.05
    Á
    0.05
    Activations Density 0.001%

    No Known Activations