© 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. 65471
    Prev
    Next
    INDEX
    Explanations

    adenosyl, ado, rado

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

    Japanese names and specific scientific terminology, particularly chemical compound names.

    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
    の神
    -0.88
    ffy
    -0.87
     maybe
    -0.81
    嗶
    -0.80
     Claim
    -0.77
    ulos
    -0.76
    couvrir
    -0.75
     Wide
    -0.75
    tion
    -0.73
    れてる
    -0.72
    POSITIVE LOGITS
    ztály
    1.00
    的事情
    0.79
     ann
    0.78
     Dobson
    0.78
     iniquity
    0.76
    нью
    0.76
     domesti
    0.75
    setOption
    0.74
     laba
    0.73
    分割
    0.73
    Activations Density 0.045%

    No Known Activations