© 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. 118336
    Prev
    Next
    INDEX
    Explanations

    digital content and online media

    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
     আশ্চর্য
    -0.06
    榃
    -0.06
     заменить
    -0.06
    three
    -0.06
    หลาย
    -0.06
    Items
    -0.06
     herbicide
    -0.06
     пользоваться
    -0.06
    Ｗ
    -0.06
    five
    -0.06
    POSITIVE LOGITS
    غال
    0.07
     narod
    0.06
     monstru
    0.06
    🗣
    0.06
    consistent
    0.06
    先把
    0.06
     जनता
    0.06
     auditorium
    0.06
     consistent
    0.06
     sustained
    0.06
    Activations Density 0.010%

    No Known Activations