© 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. 117050
    Prev
    Next
    INDEX
    Explanations

    size, status, time variations

    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
    你们
    -0.07
     biraz
    -0.07
     Krankheit
    -0.07
     epistle
    -0.06
     사람들이
    -0.06
    少し
    -0.06
     بیشتر
    -0.06
    স্তক
    -0.06
     अधिकतर
    -0.06
    もう少し
    -0.06
    POSITIVE LOGITS
     V
    0.06
    影响
    0.06
     An
    0.05
     Mal
    0.05
     M
    0.05
     Ar
    0.05
     Super
    0.05
    নিষ
    0.05
     H
    0.05
     influences
    0.05
    Activations Density 0.001%

    No Known Activations