© 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. 119072
    Prev
    Next
    INDEX
    Explanations

    cities, places, and biological suffixes

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

    city or location names.

    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
    雠
    -2.77
    啭
    -2.50
    🫅
    -2.48
    '
    -2.42
    ྕ
    -2.39
    侔
    -2.36
    樒
    -2.33
    鬭
    -2.28
    讦
    -2.20
    泚
    -2.17
    POSITIVE LOGITS
    b
    2.66
    戗
    2.48
    𖥧
    2.41
     “
    2.38
    .”
    2.36
    e
    2.36
    T
    2.31
    ⦊
    2.30
    .“
    2.22
    褡
    2.19
    Activations Density 0.145%

    No Known Activations