© 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. 120656
    Prev
    Next
    INDEX
    Explanations

    operations, fatal, value, tokens

    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
    ☆☆
    -0.06
     pacif
    -0.06
     samba
    -0.06
     ট্যাংক
    -0.06
    शुल्क
    -0.06
    ቪ
    -0.06
     Stafford
    -0.06
    ojn
    -0.05
     ड्यू
    -0.05
    rei
    -0.05
    POSITIVE LOGITS
     indirect
    0.07
     این
    0.06
    实际上
    0.06
    counted
    0.06
     दवाओं
    0.06
     மற்ற
    0.06
     বাইরে
    0.06
     végétale
    0.06
    ほん
    0.06
     इन्हीं
    0.06
    Activations Density 0.030%

    No Known Activations