© 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. 41573
    Prev
    Next
    INDEX
    Explanations

    G-Unit, G-Truc, G-CSF

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

    hyphenated terms with "G-" prefix, such as G-Unit, G-CSF, or G-truc.

    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
    塤
    -2.16
     häufig
    -2.11
    ၅
    -2.03
     beginning
    -1.96
     five
    -1.87
     That
    -1.86
     valioso
    -1.85
     designated
    -1.85
     wusste
    -1.84
     three
    -1.81
    POSITIVE LOGITS
    泚
    2.23
    ]
    2.17
     inequ
    1.96
    2
    1.85
     incongru
    1.80
     تاکید
    1.80
     ihres
    1.78
    ){
    1.74
     pertin
    1.73
     exasper
    1.73
    Activations Density 0.017%

    No Known Activations