© 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. 117522
    Prev
    Next
    INDEX
    Explanations

    connection between two things

    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
    雙
    -0.07
     wherever
    -0.07
     مزد
    -0.07
     harmonious
    -0.07
     dual
    -0.06
     двой
    -0.06
    的双
    -0.06
     holo
    -0.06
     blending
    -0.06
     partenaire
    -0.06
    POSITIVE LOGITS
     directly
    0.06
    Word
    0.06
     characters
    0.06
    rak
    0.06
     শব্দের
    0.06
     literate
    0.06
    視聴
    0.06
    㴡
    0.06
     dissatisfaction
    0.06
     word
    0.05
    Activations Density 0.041%

    No Known Activations