© 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. 130044
    Prev
    Next
    INDEX
    Explanations

    LABYRINTH, GLOBAL SCOPE, Jessica Chastain, Q:

    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
     क्रीम
    -0.07
     ETFs
    -0.07
    💈
    -0.06
     поиска
    -0.06
     outsourcing
    -0.06
    Inspection
    -0.06
     seeking
    -0.06
     Луч
    -0.06
    folios
    -0.06
     искать
    -0.06
    POSITIVE LOGITS
     oxygen
    0.06
     reversal
    0.06
     பக்தர்கள்
    0.06
     Atmospheric
    0.06
     Zeta
    0.06
    呈现
    0.06
     Oxygen
    0.06
    氮
    0.05
    有很多
    0.05
     chemistry
    0.05
    Activations Density 0.001%

    No Known Activations