© 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. 117459
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    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
     Smok
    -0.06
     after
    -0.06
    after
    -0.06
     beliefs
    -0.06
    ហារ
    -0.06
    Ɔ
    -0.06
     accompagné
    -0.06
     selepas
    -0.06
     setShow
    -0.06
     glossary
    -0.06
    POSITIVE LOGITS
     nessuna
    0.07
    沒有
    0.06
     demasi
    0.06
     centena
    0.06
     hundreds
    0.06
     dile
    0.06
     keine
    0.06
     Improve
    0.06
     нет
    0.06
     centaines
    0.06
    Activations Density 0.001%

    No Known Activations