© 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. 117681
    Prev
    Next
    INDEX
    Explanations

    full text or entirety

    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
     그래서
    -0.06
    夏の
    -0.06
     종류
    -0.06
     찾
    -0.06
     receive
    -0.06
     фина
    -0.06
    translator
    -0.06
     uncovered
    -0.05
    คู่
    -0.05
     först
    -0.05
    POSITIVE LOGITS
    ទាំងអស់
    0.06
     长
    0.06
     savons
    0.06
     canh
    0.06
    स्त्र
    0.06
     laser
    0.06
    ždy
    0.06
    每一次
    0.06
     bers
    0.06
     ALL
    0.06
    Activations Density 0.007%

    No Known Activations