© 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. 119936
    Prev
    Next
    INDEX
    Explanations

    discover meditation

    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
     the
    -0.07
     several
    -0.06
     some
    -0.06
     dozens
    -0.06
     each
    -0.05
     our
    -0.05
    ieb
    -0.05
     both
    -0.05
     Horn
    -0.05
    季度
    -0.05
    POSITIVE LOGITS
     الم
    0.07
     의
    0.07
     wykorzyst
    0.06
    কোত্তর
    0.06
     신
    0.06
    ‟
    0.06
     scriptures
    0.06
     مولانا
    0.06
    ના
    0.06
    ですね
    0.06
    Activations Density 0.015%

    No Known Activations