© 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. 129029
    Prev
    Next
    INDEX
    Explanations

    high power, energy, or duty

    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
     সিলে
    -0.06
    চা
    -0.06
     selecting
    -0.06
     plantilla
    -0.06
     الثانوي
    -0.06
     statewide
    -0.06
     अनिवार्य
    -0.06
    hes
    -0.06
    ચા
    -0.05
    ifices
    -0.05
    POSITIVE LOGITS
     افرادی
    0.08
    密切
    0.07
     mientras
    0.07
     estos
    0.06
    這
    0.06
    不知
    0.06
    维持
    0.06
    与之
    0.06
     diesen
    0.06
    izie
    0.06
    Activations Density 0.011%

    No Known Activations