© 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. 42187
    Prev
    Next
    INDEX
    Explanations

    skin testing and conditions

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

    mentions of human or animal skin in medical or scientific contexts.

    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
     It
    -3.02
     –
    -2.63
    ↵
    -2.61
     About
    -2.56
    es
    -2.50
    It
    -2.42
    al
    -2.42
     Also
    -2.34
    IN
    -2.31
    서는
    -2.25
    POSITIVE LOGITS
    ৹
    2.81
    薺
    2.73
    ⬮
    2.58
    ギュア
    2.41
    حتی
    2.41
     帅气
    2.33
     hacían
    2.31
    鱨
    2.30
    总裁
    2.28
     realizando
    2.27
    Activations Density 0.012%

    No Known Activations