© 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. 117250
    Prev
    Next
    INDEX
    Explanations

    alignment tags

    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
     café
    -0.06
     ఉంటు
    -0.06
     snacks
    -0.06
     snack
    -0.06
    contour
    -0.06
     consideration
    -0.06
     Ра
    -0.05
     unregulated
    -0.05
    WindowState
    -0.05
    doing
    -0.05
    POSITIVE LOGITS
     يح
    0.06
     faithfulness
    0.06
    thr
    0.06
    秇
    0.06
    Danh
    0.06
     forbid
    0.06
    帖子
    0.06
     prohibit
    0.06
    लेख
    0.06
    ブログ
    0.06
    Activations Density 0.001%

    No Known Activations