© 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. 120161
    Prev
    Next
    INDEX
    Explanations

    import statements

    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
    During
    -0.06
     This
    -0.06
    When
    -0.06
     progres
    -0.06
    This
    -0.06
    parent
    -0.06
    prog
    -0.06
    request
    -0.06
     terlalu
    -0.05
    POSITIVE LOGITS
     use
    0.07
     vielf
    0.06
     hated
    0.06
    持有
    0.06
     bequem
    0.06
    startsWith
    0.06
    ☂
    0.06
     gerne
    0.06
    িন্দ
    0.06
    nums
    0.06
    Activations Density 0.005%

    No Known Activations