© 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. 34-GEMMASCOPE-RES-131K
    7. 75868
    Prev
    Next
    INDEX
    Explanations

    flexion, extension, flexor

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

    CSS flexbox properties and code related to flexible layouts.

    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_34/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
     शिक्ष
    -0.75
    бря
    -0.74
     mehr
    -0.73
     Insets
    -0.71
    ʚ
    -0.70
    　※
    -0.70
    cangan
    -0.69
     Konzer
    -0.69
    вети
    -0.69
    mitt
    -0.68
    POSITIVE LOGITS
     flex
    2.61
     Flex
    2.19
    flex
    2.19
     flexing
    2.05
     flexion
    1.99
    Flex
    1.96
     FLEX
    1.78
    flexDirection
    1.72
    FLEX
    1.68
    屈
    1.09
    Activations Density 0.023%

    No Known Activations