© 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. 128325
    Prev
    Next
    INDEX
    Explanations

    variable declaration keywords

    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
    一
    -0.07
    安心
    -0.06
     misalnya
    -0.06
    ('
    -0.06
     atmosphere
    -0.06
    鑒
    -0.06
    ('.
    -0.06
     安心
    -0.06
    Ᏹ
    -0.06
    因此
    -0.06
    POSITIVE LOGITS
     use
    0.06
     séptimo
    0.06
     gaji
    0.06
     நார்ச்சத்து
    0.06
    gtr
    0.06
     två
    0.06
     elegante
    0.06
     রয়েছে
    0.05
    はありません
    0.05
    했고
    0.05
    Activations Density 0.001%

    No Known Activations