© 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. 130941
    Prev
    Next
    INDEX
    Explanations

    foreign language phrases and academic contexts

    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
     incredibly
    -0.06
    ruci
    -0.06
     assaulting
    -0.06
    麾
    -0.05
     supposed
    -0.05
     purported
    -0.05
     several
    -0.05
    Administrator
    -0.05
    impinan
    -0.05
     seeking
    -0.05
    POSITIVE LOGITS
    的地方
    0.08
     있습니다
    0.06
     retrouve
    0.06
     '';
    0.06
     endroit
    0.06
     Размер
    0.06
    場所
    0.06
    巢
    0.06
     puedo
    0.06
     voltaje
    0.06
    Activations Density 0.022%

    No Known Activations