© 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. 118470
    Prev
    Next
    INDEX
    Explanations

    dioxide

    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
     για
    -0.07
     для
    -0.06
     searching
    -0.06
     for
    -0.06
     مثل
    -0.06
     or
    -0.06
     när
    -0.06
     뛰어
    -0.06
     หรือ
    -0.06
    ertain
    -0.06
    POSITIVE LOGITS
     the
    0.07
    हमारी
    0.06
    Ironically
    0.06
     ഏക
    0.06
    Nor
    0.06
     ≈
    0.06
     permit
    0.06
    mostly
    0.06
     prevents
    0.06
     permiten
    0.06
    Activations Density 0.012%

    No Known Activations