© 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. 119313
    Prev
    Next
    INDEX
    Explanations

    property rights

    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
     вас
    -0.06
     انتہائی
    -0.06
     its
    -0.06
     automóvil
    -0.06
    更加
    -0.06
     resiliency
    -0.06
     truly
    -0.06
    yawa
    -0.06
    انية
    -0.05
     نها
    -0.05
    POSITIVE LOGITS
    enough
    0.06
     onlookers
    0.06
     ويكيميديا
    0.06
    ếng
    0.06
    existing
    0.06
     생각
    0.06
     Ched
    0.06
     좋은
    0.06
    ﾄ
    0.06
    ᴋ
    0.06
    Activations Density 0.001%

    No Known Activations