© 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. 118522
    Prev
    Next
    INDEX
    Explanations

    **jail, brig, prison, detention**

    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
     histoires
    -0.07
     each
    -0.07
     сервис
    -0.06
    Most
    -0.06
     거의
    -0.06
     meisten
    -0.06
     far
    -0.06
    ائج
    -0.06
    Each
    -0.06
     mostly
    -0.06
    POSITIVE LOGITS
     devait
    0.06
     homemade
    0.06
     Wesleyan
    0.06
     need
    0.06
    汇报
    0.06
     těchto
    0.06
     unut
    0.05
     Paine
    0.05
     والت
    0.05
    week
    0.05
    Activations Density 0.002%

    No Known Activations