© 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. 117529
    Prev
    Next
    INDEX
    Explanations

    tab completion

    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
     ஏதாவது
    -0.06
     లై
    -0.06
    இந்நிலையில்
    -0.06
     뭔가
    -0.06
     léger
    -0.06
     légère
    -0.06
    getItem
    -0.06
    വിടെ
    -0.06
    কাঁ
    -0.06
     comenzó
    -0.06
    POSITIVE LOGITS
     распростра
    0.06
     assuring
    0.06
    知道
    0.06
     zust
    0.06
     systemic
    0.06
    他和
    0.06
     subsequent
    0.06
     lung
    0.06
     공식
    0.06
    থিত
    0.06
    Activations Density 0.002%

    No Known Activations