© 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. 117925
    Prev
    Next
    INDEX
    Explanations

    6

    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
    邇
    -0.07
     otras
    -0.07
     অন্যান্য
    -0.07
     otomatik
    -0.07
     also
    -0.06
     আৰু
    -0.06
     outras
    -0.06
     другие
    -0.06
    ២
    -0.06
     سایر
    -0.06
    POSITIVE LOGITS
     a
    0.08
     an
    0.07
    皇帝
    0.06
     one
    0.06
     sparingly
    0.06
    微妙
    0.05
     enthous
    0.05
     sikre
    0.05
     Judicial
    0.05
     huyện
    0.05
    Activations Density 0.002%

    No Known Activations