© 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. 116231
    Prev
    Next
    INDEX
    Explanations

    list(data), menu, DB

    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
     කු
    -0.06
     forman
    -0.06
     крупных
    -0.06
     ominous
    -0.06
     extraneous
    -0.06
     tạp
    -0.06
     yawning
    -0.06
     you
    -0.06
     કહ્યું
    -0.06
     Accenture
    -0.06
    POSITIVE LOGITS
     wraz
    0.07
     geheel
    0.06
    Possibly
    0.06
     vielleicht
    0.06
     возможно
    0.06
     ناخذ
    0.06
    设有
    0.06
    äle
    0.06
    有可能
    0.06
     Taq
    0.06
    Activations Density 0.030%

    No Known Activations