© 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. 121011
    Prev
    Next
    INDEX
    Explanations

    numbers and technical terms

    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
     উভয়
    -0.06
     updating
    -0.06
     inflating
    -0.06
     electronic
    -0.06
    என்ன
    -0.06
     stylish
    -0.06
    ħ
    -0.06
     Kit
    -0.06
    智能
    -0.06
    使得
    -0.05
    POSITIVE LOGITS
     لهذه
    0.08
     வளர்ச்சி
    0.07
     অন্তত
    0.07
     to
    0.07
     these
    0.07
    ጠር
    0.06
    internal
    0.06
     этой
    0.06
     algunos
    0.06
    的に
    0.06
    Activations Density 0.015%

    No Known Activations