© 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. 130303
    Prev
    Next
    INDEX
    Explanations

    script tags and 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
     dalších
    -0.07
     وال
    -0.07
    ਕੇ
    -0.06
    ックレス
    -0.06
     மற்ற
    -0.06
    Other
    -0.06
    োপুরি
    -0.06
     autres
    -0.06
     سایر
    -0.06
     örne
    -0.06
    POSITIVE LOGITS
     gigantic
    0.06
     pust
    0.06
     then
    0.06
     hermoso
    0.06
     módulo
    0.06
     titanium
    0.06
     ওঠা
    0.06
     frequented
    0.06
    ंडीगढ़
    0.06
    Vendo
    0.06
    Activations Density 0.001%

    No Known Activations