© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26185
    Prev
    Next
    INDEX
    Explanations

    the invention relates to

    np_acts-logits-general · gemini-2.5-flash-lite

    text related to patents and inventions, particularly focusing on technical descriptions beginning with "The invention relates to."

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     technik
    -0.94
     lás
    -0.91
     liczba
    -0.90
     encamin
    -0.89
    种类
    -0.88
    ZZA
    -0.88
     giras
    -0.86
     dát
    -0.85
     esquí
    -0.85
    ⌀
    -0.84
    POSITIVE LOGITS
     still
    1.00
    still
    0.87
    있
    0.84
    面積
    0.84
    規模
    0.84
     STILL
    0.81
     簡単
    0.81
     possesso
    0.80
     Paesi
    0.80
    STILL
    0.79
    Activations Density 0.003%

    No Known Activations