© 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. 117247
    Prev
    Next
    INDEX
    Explanations

    Sports teams playing each other

    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
     previous
    -0.07
     particularly
    -0.07
     blant
    -0.06
    .*;
    -0.06
     menurut
    -0.06
     one
    -0.06
    几年
    -0.06
     tahun
    -0.06
    去年
    -0.06
    又是
    -0.06
    POSITIVE LOGITS
     their
    0.08
    他们的
    0.08
     അവരുടെ
    0.08
     with
    0.08
    与
    0.07
    他們的
    0.07
     leurs
    0.07
     चित्र
    0.07
     njihov
    0.07
     তাদের
    0.07
    Activations Density 0.012%

    No Known Activations