© 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. 128340
    Prev
    Next
    INDEX
    Explanations

    begins

    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
    If
    -0.07
     স্পষ্টভাবে
    -0.06
     ถ้า
    -0.06
    unless
    -0.06
    Unless
    -0.06
     operate
    -0.06
    operate
    -0.06
    chang
    -0.06
    lll
    -0.06
     Yearly
    -0.06
    POSITIVE LOGITS
     being
    0.08
     філь
    0.07
    になっている
    0.06
     agak
    0.06
    기술
    0.06
     having
    0.06
     sudah
    0.06
    이라고
    0.06
     what
    0.06
     almost
    0.06
    Activations Density 0.015%

    No Known Activations