© 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. 119408
    Prev
    Next
    INDEX
    Explanations

    listener or observer

    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
    points
    -0.06
     навчання
    -0.06
     frecuente
    -0.06
     fréquemment
    -0.06
    лександ
    -0.06
    યો
    -0.06
    ത്തിനെ
    -0.06
    Environmental
    -0.06
    避免
    -0.06
     व्यापक
    -0.06
    POSITIVE LOGITS
     aceptar
    0.06
     বসবাসের
    0.06
     accett
    0.06
    }}=-\
    0.06
    news
    0.05
     હું
    0.05
     і
    0.05
     accept
    0.05
     মাপ
    0.05
    私は
    0.05
    Activations Density 0.004%

    No Known Activations