© 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. 117007
    Prev
    Next
    INDEX
    Explanations

    who, those, quit

    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
     utilizar
    -0.07
     этих
    -0.07
    現
    -0.06
    constructing
    -0.06
     saya
    -0.06
     vorhand
    -0.06
     পুরনো
    -0.06
     Сегодня
    -0.06
     oggi
    -0.06
     constructing
    -0.06
    POSITIVE LOGITS
    和他
    0.06
    for
    0.06
     soul
    0.06
     معه
    0.06
    וג
    0.06
    visit
    0.06
    不
    0.06
     Photographer
    0.05
    soul
    0.05
     she
    0.05
    Activations Density 0.022%

    No Known Activations