© 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. 128682
    Prev
    Next
    INDEX
    Explanations

    or later

    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
     aspects
    -0.07
     tidigare
    -0.06
     yang
    -0.06
    since
    -0.06
     dimana
    -0.06
     skoro
    -0.06
     ব্যাবস্থা
    -0.06
    걔
    -0.06
     อัน
    -0.06
     gốc
    -0.06
    POSITIVE LOGITS
    셀
    0.06
    ždy
    0.06
     pokazuje
    0.06
    每月
    0.06
     अपराध
    0.05
     fizz
    0.05
     poverty
    0.05
     الانترنت
    0.05
     help
    0.05
     cheap
    0.05
    Activations Density 0.001%

    No Known Activations