© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130413
    Prev
    Next
    INDEX
    Explanations

    real estate and professional roles

    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
     roadblock
    -0.07
     plan
    -0.07
     current
    -0.06
     noteworthy
    -0.06
    澥
    -0.06
     successes
    -0.06
     உள்
    -0.06
    藠
    -0.06
    。。
    -0.06
     toege
    -0.06
    POSITIVE LOGITS
     גם
    0.07
     ook
    0.06
     人
    0.06
    या
    0.06
    ;
    0.06
     regardless
    0.06
    虽然
    0.06
    또한
    0.06
     և
    0.06
     también
    0.05
    Activations Density 0.001%

    No Known Activations