© 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. 120591
    Prev
    Next
    INDEX
    Explanations

    Scythian or Persian artifacts or locations

    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
     தவிர
    -0.07
    正直
    -0.06
    事故
    -0.06
     leves
    -0.06
     मिश्र
    -0.06
    ausible
    -0.06
     rookies
    -0.06
     choices
    -0.06
     প্রজন্ম
    -0.06
    ုံ
    -0.06
    POSITIVE LOGITS
     their
    0.09
     তাদের
    0.08
     их
    0.07
     അവരുടെ
    0.07
     jejich
    0.06
     OST
    0.06
    他們的
    0.06
    usahaan
    0.06
     our
    0.06
     അവര്‍
    0.06
    Activations Density 0.004%

    No Known Activations