© 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. 10-GEMMASCOPE-RES-131K
    7. 75463
    Prev
    Next
    INDEX
    Explanations

    phenylalanine, Pheophorbide

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

    three-letter programming or technical abbreviations/terms (like 'tle', 'tify', 'thy', 'abb', 'yu', 'yu/i').

    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_10/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
    o
    -3.56
    a
    -3.28
    ar
    -2.94
    ll
    -2.89
     oleh
    -2.88
    d
    -2.84
    rs
    -2.75
    al
    -2.70
    es
    -2.69
      
    -2.63
    POSITIVE LOGITS
    زيل
    3.23
    瑧
    2.98
     彈
    2.73
    廰
    2.73
     soñ
    2.67
    籥
    2.66
    褔
    2.56
    讴
    2.56
    崤
    2.56
    ꪔ
    2.53
    Activations Density 0.032%

    No Known Activations