© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62612
    Prev
    Next
    INDEX
    Explanations

    clonidine, brimonidine, antagonist

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

    chemical and pharmaceutical compounds, particularly focusing on medications and their molecular structures.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ggf
    -0.78
    Sik
    -0.78
     REPORTING
    -0.72
    ješ
    -0.72
    エリ
    -0.72
    десь
    -0.71
     inwest
    -0.69
    fektions
    -0.68
     WebDriverWait
    -0.68
     replication
    -0.67
    POSITIVE LOGITS
     Ramsay
    0.82
     NCR
    0.79
    Cpu
    0.78
    شتر
    0.77
     ADHD
    0.77
    chiat
    0.76
     NSE
    0.75
    ῥ
    0.74
     PFA
    0.73
     Balkan
    0.73
    Activations Density 0.032%

    No Known Activations