© 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. 12565
    Prev
    Next
    INDEX
    Explanations

    orange fruit/color

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

    references to the color orange or orange-colored objects.

    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
    を始め
    -2.42
    鯢
    -2.38
    髎
    -2.31
    ндарт
    -2.17
    ଢ
    -2.03
    躂
    -2.03
    鷽
    -2.00
    跸
    -2.00
     diseñ
    -1.99
     花纹
    -1.99
    POSITIVE LOGITS
    ↵↵
    2.81
    
    2.14
    N
    2.09
    ции
    1.98
    ка
    1.95
    」。
    1.88
     inherently
    1.82
    »,
    1.80
     становится
    1.80
     be
    1.80
    Activations Density 0.007%

    No Known Activations