© 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. 117099
    Prev
    Next
    INDEX
    Explanations

    band 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
     vontade
    -0.06
     няколко
    -0.06
    amız
    -0.06
    
    -0.06
     Netherlands
    -0.06
     bernama
    -0.06
     Scripps
    -0.06
     ஆரம்பித்த
    -0.05
    amm
    -0.05
     Controls
    -0.05
    POSITIVE LOGITS
     данном
    0.07
    Captcha
    0.06
     these
    0.06
     данной
    0.06
     இவற்ற
    0.06
     इन
    0.06
    在這個
    0.06
     هذه
    0.06
     этой
    0.06
    डू
    0.06
    Activations Density 0.025%

    No Known Activations