© 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. 120512
    Prev
    Next
    INDEX
    Explanations

    rehearing denied

    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
     разных
    -0.06
     базы
    -0.06
     of
    -0.06
     Raises
    -0.06
    ه‌های
    -0.06
     COMPUTER
    -0.06
    endent
    -0.06
     Derived
    -0.06
     Casinos
    -0.06
     різних
    -0.06
    POSITIVE LOGITS
     عادي
    0.06
     معنات
    0.06
     نص
    0.06
     détente
    0.05
     civilized
    0.05
    ।...
    0.05
    etrot
    0.05
    涵
    0.05
    ław
    0.05
     lawn
    0.05
    Activations Density 0.004%

    No Known Activations