© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118242
    Prev
    Next
    INDEX
    Explanations

    sugar adenosine

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

    crystallographic notation and terms related to molecular structures in scientific papers.

    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_34/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
    ulus
    -0.74
     pageNo
    -0.73
    æng
    -0.70
    生日
    -0.70
     ejecutivo
    -0.69
     ಮತ್ತು
    -0.69
    MAZ
    -0.69
    Nam
    -0.68
    machten
    -0.68
    oramic
    -0.67
    POSITIVE LOGITS
     point
    1.04
     Point
    1.01
    Point
    0.94
     punto
    0.82
    point
    0.82
    POINT
    0.79
     च
    0.76
    えば
    0.69
     configuration
    0.69
     centros
    0.69
    Activations Density 0.055%

    No Known Activations