© 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. 871
    Prev
    Next
    INDEX
    Explanations

    Norwalk, Horowitz, chisel

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

    technical terms, industry terminology, and specific named entities across different domains and languages.

    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
    0
    -3.73
     Despite
    -3.41
     Because
    -3.34
     Unlike
    -3.23
     Although
    -3.13
    Despite
    -3.08
     Considering
    -2.94
     Depending
    -2.92
     Undoubtedly
    -2.92
     Interestingly
    -2.84
    POSITIVE LOGITS
    饪
    3.05
    圌
    3.02
    蓐
    2.97
    a
    2.81
    漚
    2.80
    鲧
    2.75
    糨
    2.75
    kinda
    2.70
    🫃
    2.63
    
    2.59
    Activations Density 0.003%

    No Known Activations