© 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. 128844
    Prev
    Next
    INDEX
    Explanations

    epithelial cells

    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
    output
    -0.07
    输出
    -0.06
     Comme
    -0.06
     foiled
    -0.06
    comme
    -0.06
    なか
    -0.06
    iris
    -0.06
    Spell
    -0.06
    Doll
    -0.06
     other
    -0.06
    POSITIVE LOGITS
     überras
    0.06
    probably
    0.06
     tournaments
    0.06
    ጠቀ
    0.06
     कई
    0.06
    拍摄
    0.06
     अपहरण
    0.06
     tournament
    0.06
     長
    0.05
     bạn
    0.05
    Activations Density 0.016%

    No Known Activations