© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 128697
    Prev
    Next
    INDEX
    Explanations

    lists and enumerations

    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
     an
    -0.08
     a
    -0.07
     (?)
    -0.07
     Johannesburg
    -0.07
     與
    -0.07
     określ
    -0.07
     上海
    -0.07
     ebenso
    -0.06
     거고
    -0.06
     बनाम
    -0.06
    POSITIVE LOGITS
     نئے
    0.06
     cultures
    0.05
     новый
    0.05
    なども
    0.05
     preprint
    0.05
     بحيث
    0.05
     যাতে
    0.05
     सेंचुरी
    0.05
     हफ्ते
    0.05
     fprintf
    0.05
    Activations Density 0.086%

    No Known Activations