© 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. 117426
    Prev
    Next
    INDEX
    Explanations

    players and coaches names

    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
     pygame
    -0.06
     niewiel
    -0.06
     কয়েক
    -0.06
    reference
    -0.06
     droid
    -0.06
    沣
    -0.06
     utwor
    -0.06
     (*
    -0.06
     hostility
    -0.06
     only
    -0.06
    POSITIVE LOGITS
     কর্তব্য
    0.06
    vintage
    0.06
    दिन
    0.06
    
    0.06
     XIX
    0.06
    getNumber
    0.06
     മണിക്ക
    0.06
     väga
    0.06
     elevator
    0.06
     Мето
    0.06
    Activations Density 0.004%

    No Known Activations