© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60222
    Prev
    Next
    INDEX
    Explanations

    proteins and genes

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

    biochemical and genetic terminology, particularly related to proteins, enzymes, and genetic markers.

    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
    بول
    -0.71
     Nile
    -0.68
     domic
    -0.66
     제공
    -0.66
    붕
    -0.65
     Domestic
    -0.64
     Portion
    -0.64
    endu
    -0.63
    NLS
    -0.63
     Fill
    -0.63
    POSITIVE LOGITS
    proper
    1.13
     proper
    1.13
    Proper
    1.10
     PROPER
    1.02
     Proper
    0.93
     phosp
    0.91
     ester
    0.74
     Geme
    0.72
     GOT
    0.72
    лык
    0.72
    Activations Density 0.196%

    No Known Activations