© 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. 128883
    Prev
    Next
    INDEX
    Explanations

    event listings or dates

    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
     zaradi
    -0.06
     its
    -0.06
    輕
    -0.06
    Its
    -0.06
     Its
    -0.06
     why
    -0.06
     giggle
    -0.06
     শাব
    -0.06
     зни
    -0.06
     ग्राहक
    -0.06
    POSITIVE LOGITS
     পশ্চিমে
    0.06
     событий
    0.06
     огром
    0.06
     หมด
    0.06
    iel
    0.06
     αυτά
    0.06
     Obec
    0.06
     moles
    0.06
     уже
    0.06
     الآن
    0.06
    Activations Density 0.024%

    No Known Activations