© 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. 117129
    Prev
    Next
    INDEX
    Explanations

    conditional start of phrases

    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
     até
    -0.07
     until
    -0.07
     некоторые
    -0.06
    াদান
    -0.06
    উন্ট
    -0.06
     bazı
    -0.06
     ק
    -0.06
    until
    -0.06
     फिगर
    -0.06
     сотрудник
    -0.06
    POSITIVE LOGITS
    梁
    0.06
    !!!!
    0.06
     COP
    0.06
    !!!!!
    0.06
    ♡
    0.05
    rich
    0.05
    zh
    0.05
    bou
    0.05
    apura
    0.05
    anson
    0.05
    Activations Density 0.002%

    No Known Activations