© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 129021
    Prev
    Next
    INDEX
    Explanations

    dollar amounts or currency symbols

    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
     किसे
    -0.06
     without
    -0.06
    完全
    -0.06
     babe
    -0.06
    将于
    -0.06
     kjer
    -0.05
    サンプル
    -0.05
     limpiar
    -0.05
     przyn
    -0.05
     całkow
    -0.05
    POSITIVE LOGITS
    となった
    0.06
     একসঙ্গে
    0.06
     collaboratively
    0.06
     once
    0.06
     совместно
    0.06
    となりました
    0.06
     പിന്നീ
    0.06
    еди
    0.06
     thereafter
    0.06
    当初
    0.06
    Activations Density 0.001%

    No Known Activations