© 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. 119261
    Prev
    Next
    INDEX
    Explanations

    html tag attributes and css properties

    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
    आपको
    -0.07
     subtiliter
    -0.07
     ekstra
    -0.06
     dalam
    -0.06
     ostensibly
    -0.06
     duvar
    -0.06
     mér
    -0.06
    اضره
    -0.06
    ড্রিম
    -0.06
    #%%
    -0.06
    POSITIVE LOGITS
    There
    0.07
    <strong>
    0.07
    0.06
    <0xE3>
    0.06
    <b>
    0.06
    
    0.06
    Let
    0.06
    This
    0.06
    ویں
    0.06
    `
    0.06
    Activations Density 0.013%

    No Known Activations