© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128542
    Prev
    Next
    INDEX
    Explanations

    closed, sealed, isolated

    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
     differing
    -0.07
     quiescent
    -0.06
     внед
    -0.06
     уничто
    -0.06
     Stealth
    -0.06
     hükü
    -0.06
    ucksack
    -0.06
    itations
    -0.06
    yní
    -0.06
     Always
    -0.06
    POSITIVE LOGITS
    足够
    0.07
     çev
    0.06
    closed
    0.06
     particular
    0.06
     has
    0.06
     change
    0.05
     가져
    0.05
    闭
    0.05
     சூழ
    0.05
    ębior
    0.05
    Activations Density 0.025%

    No Known Activations