© 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. 119989
    Prev
    Next
    INDEX
    Explanations

    results and announcements

    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
     tangerine
    -0.06
     CGRect
    -0.06
     ;)
    -0.06
    రించే
    -0.06
     rescue
    -0.06
     peluang
    -0.06
    шуу
    -0.06
    (/\
    -0.05
     अगर
    -0.05
    ция
    -0.05
    POSITIVE LOGITS
     publicly
    0.06
     sometimes
    0.06
     published
    0.06
     anún
    0.06
     Dax
    0.06
     bekannt
    0.06
     Resource
    0.06
     кін
    0.06
    Acknowledgements
    0.06
     publicized
    0.06
    Activations Density 0.015%

    No Known Activations