© 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. 130829
    Prev
    Next
    INDEX
    Explanations

    ordered phases and transitions

    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
     추천
    -0.07
     recommendation
    -0.07
     enviado
    -0.07
    常に
    -0.07
     nonchal
    -0.07
     rapid
    -0.07
    andaag
    -0.07
     frequently
    -0.07
     all
    -0.07
     verify
    -0.06
    POSITIVE LOGITS
    website
    0.07
    既存
    0.07
     территориа
    0.06
    webs
    0.05
    ंद्व
    0.05
     കരാ
    0.05
    writers
    0.05
     divid
    0.05
     señ
    0.05
     ي
    0.05
    Activations Density 0.004%

    No Known Activations