© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130265
    Prev
    Next
    INDEX
    Explanations

    manage, delete, move actions

    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
    <eos>
    -0.07
     .....
    -0.07
    .....
    -0.06
     .......
    -0.06
    .......
    -0.06
    ........
    -0.06
    ....
    -0.06
     following
    -0.06
     ......
    -0.06
    ларда
    -0.06
    POSITIVE LOGITS
     Даже
    0.07
     Как
    0.07
     as
    0.07
    ouns
    0.06
     так
    0.06
    Humans
    0.06
    étais
    0.06
     Brian
    0.06
    别人的
    0.06
     प्रत्येक
    0.06
    Activations Density 0.002%

    No Known Activations