© 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. 119904
    Prev
    Next
    INDEX
    Explanations

    subjective opinion or experience

    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
     போக்குவர
    -0.07
     evening
    -0.07
     intricacies
    -0.06
     evenings
    -0.06
     realistic
    -0.06
     nights
    -0.06
     scientific
    -0.06
     magnificent
    -0.06
     miraculous
    -0.06
     meticulous
    -0.06
    POSITIVE LOGITS
     sauf
    0.06
    認定
    0.06
    認為
    0.06
     অধিকাংশই
    0.06
    Bounce
    0.06
     meiner
    0.06
     sugi
    0.06
     либо
    0.06
     suspected
    0.06
     популяр
    0.06
    Activations Density 0.010%

    No Known Activations