© 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. 10-GEMMASCOPE-RES-131K
    4. 12060
    Prev
    Next
    INDEX
    Explanations

    lexer, cholera, Rutgers, volcanic, Shader, MySQL

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

    technical terms related to programming languages, disease names, and specialized technical vocabulary.

    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
    缡
    -2.86
    d
    -2.83
    n
    -2.64
    ates
    -2.56
    孓
    -2.50
    焄
    -2.36
    
    -2.36
    珢
    -2.22
    poptotic
    -2.20
     花卉
    -2.16
    POSITIVE LOGITS
    }$
    3.42
    蛲
    2.88
     jednu
    2.66
    ዡ
    2.61
     Problemen
    2.56
    橚
    2.55
     venerable
    2.55
     delapan
    2.50
    pisah
    2.48
     Geset
    2.42
    Activations Density 0.006%

    No Known Activations