© 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. 128918
    Prev
    Next
    INDEX
    Explanations

    medical abbreviations and statistics

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

    sentences that contain statistical or numerical information in academic or research text.

    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
     this
    -0.93
    ンテージ
    -0.81
     постоянно
    -0.79
    тябрь
    -0.79
    见的
    -0.77
    центри
    -0.77
     Qualitäts
    -0.76
    heses
    -0.76
    隧
    -0.75
    PTA
    -0.75
    POSITIVE LOGITS
     spécifique
    1.04
    umuz
    1.02
    响应
    0.94
    ticularly
    0.88
    onus
    0.88
     Geset
    0.85
     հղ
    0.85
    chtet
    0.85
    相关
    0.84
     TÉCN
    0.84
    Activations Density 0.476%

    No Known Activations