© 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. 1279
    Prev
    Next
    INDEX
    Explanations

    names and medical states

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

    proper names of people, companies, organizations, or medical conditions.

    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
    ’
    -3.94
    {
    -3.47
     \
    -3.17
    “
    -2.95
    o
    -2.92
    g
    -2.88
    `
    -2.81
     is
    -2.78
    j
    -2.72
    ?
    -2.72
    POSITIVE LOGITS
    ſelves
    3.05
    喾
    2.98
     рецепта
    2.92
    ྄
    2.91
    皷
    2.83
    〬
    2.80
    *}[
    2.72
    梠
    2.72
    齶
    2.63
    ᨈ
    2.61
    Activations Density 0.015%

    No Known Activations