© 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. 128493
    Prev
    Next
    INDEX
    Explanations

    body works, glass vase, soon as

    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
     ممکن
    -0.08
     mungkin
    -0.07
    かもし
    -0.07
    父母
    -0.06
    ധാ
    -0.06
     genitori
    -0.06
    อาจ
    -0.06
     Chinatown
    -0.06
     Verwendung
    -0.06
     olabilir
    -0.06
    POSITIVE LOGITS
     chocolate
    0.06
     hydrate
    0.06
     phrase
    0.06
    地域の
    0.06
    体重
    0.06
    喜歡
    0.06
     prosed
    0.06
    王国
    0.05
    hydrate
    0.05
     ਉਹ
    0.05
    Activations Density 0.034%

    No Known Activations