© 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. 120046
    Prev
    Next
    INDEX
    Explanations

    order approximation

    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
    ゆっくり
    -0.06
     lentamente
    -0.06
     udal
    -0.06
    純
    -0.06
     نظام
    -0.06
     normaal
    -0.06
    pure
    -0.05
     प
    -0.05
    ค่อย
    -0.05
     Nom
    -0.05
    POSITIVE LOGITS
     lacking
    0.07
     एकमात्र
    0.06
     العاشر
    0.06
     sbagli
    0.06
     празд
    0.06
    誤差
    0.06
     coincid
    0.06
     tantamount
    0.06
     berühm
    0.06
     alors
    0.06
    Activations Density 0.001%

    No Known Activations