© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130697
    Prev
    Next
    INDEX
    Explanations

    getsum

    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
    ี่ป
    -0.06
     worry
    -0.06
     Malang
    -0.06
     NaN
    -0.06
     কার্যকলাপ
    -0.06
     سابق
    -0.06
     cannot
    -0.06
     আনে
    -0.06
     through
    -0.06
     alleen
    -0.06
    POSITIVE LOGITS
    Sql
    0.06
     riesce
    0.06
     remercie
    0.06
     aby
    0.06
     if
    0.06
     riusc
    0.06
     ペンダント
    0.06
     auto
    0.06
    коли
    0.06
    猜测
    0.06
    Activations Density 0.001%

    No Known Activations