© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118341
    Prev
    Next
    INDEX
    Explanations

    section headers and copyright notices

    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
     digital
    -0.06
    🎉
    -0.06
    конец
    -0.06
     segera
    -0.06
    `
    -0.06
     Digital
    -0.06
    第一时间
    -0.06
    Europa
    -0.06
     imedi
    -0.06
    kur
    -0.06
    POSITIVE LOGITS
     there
    0.07
    पिछ
    0.07
     doubtful
    0.06
     तापमान
    0.06
     म्हणजेच
    0.06
     سے
    0.06
     заклю
    0.06
     специ
    0.06
     اجيب
    0.06
    担当
    0.06
    Activations Density 0.001%

    No Known Activations