© 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. 119921
    Prev
    Next
    INDEX
    Explanations

    programming language C

    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
     neuen
    -0.06
    ামি
    -0.06
    лын
    -0.06
     twor
    -0.06
     undercover
    -0.06
     consisting
    -0.06
     ব্যবহার
    -0.06
    ্ডার
    -0.06
     electr
    -0.06
     kullan
    -0.06
    POSITIVE LOGITS
    資料
    0.06
     ойнойт
    0.06
     பண்ப
    0.06
    ायला
    0.06
     वर्क
    0.06
     Aspects
    0.05
     ngữ
    0.05
    喝酒
    0.05
     промы
    0.05
     baptized
    0.05
    Activations Density 0.001%

    No Known Activations