© 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. 124168
    Prev
    Next
    INDEX
    Explanations

    carbonyl compounds, Polaris Partners, McMaster University

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

    chemical and food-related compounds, particularly words related to "carbonyl" or bakery items.

    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
     
    -3.16
    </h3>
    -2.75
    鮰
    -2.42
    い
    -2.42
    毉
    -2.39
    ࿊
    -2.38
     womit
    -2.33
    a
    -2.31
    みよう
    -2.31
     '
    -2.31
    POSITIVE LOGITS
    ſelves
    2.97
    .”
    2.75
    .’
    2.63
    敍
    2.50
    ’.
    2.47
     帳
    2.47
     到着
    2.44
    悒
    2.41
    会的
    2.41
    孓
    2.39
    Activations Density 0.007%

    No Known Activations