© 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. 117313
    Prev
    Next
    INDEX
    Explanations

    transparency

    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
     बुखार
    -0.06
    言語
    -0.06
     peinture
    -0.06
    书城
    -0.06
     modified
    -0.06
     recht
    -0.06
    招标
    -0.06
    ʇ
    -0.06
    PICTOGRAM
    -0.06
     право
    -0.06
    POSITIVE LOGITS
    Transparency
    0.07
     transparency
    0.06
     translucent
    0.06
    oof
    0.06
     deft
    0.06
     Kombat
    0.06
     transparent
    0.06
     Transparency
    0.06
     główn
    0.06
     прозра
    0.06
    Activations Density 0.004%

    No Known Activations