© 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. 118817
    Prev
    Next
    INDEX
    Explanations

    parent not

    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
    ),
    -0.06
     ফেলা
    -0.06
     espera
    -0.06
     மஞ்ச
    -0.06
     EUA
    -0.06
     )
    -0.06
    [
    -0.06
    ..
    -0.05
     ),
    -0.05
     protagonistas
    -0.05
    POSITIVE LOGITS
     coming
    0.07
     Customs
    0.06
    train
    0.06
    acceptable
    0.06
     Teles
    0.06
     arriving
    0.06
    Train
    0.06
     meinen
    0.06
     tailor
    0.06
     acceptable
    0.06
    Activations Density 0.045%

    No Known Activations