© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116017
    Prev
    Next
    INDEX
    Explanations

    event.preventDefault()

    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
    Negative Logits
     адам
    -0.06
     extens
    -0.05
     Qxd
    -0.05
    Alban
    -0.05
     وحد
    -0.05
     wenige
    -0.05
    显得
    -0.05
     حاض
    -0.05
    Days
    -0.05
    位于
    -0.05
    POSITIVE LOGITS
     ব্র্যান্ড
    0.07
     não
    0.06
    juang
    0.06
     also
    0.06
     not
    0.06
     produziert
    0.06
     placebo
    0.06
     can
    0.06
     Produ
    0.06
     Randy
    0.06
    Activations Density 0.001%

    No Known Activations