© 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. 11920
    Prev
    Next
    INDEX
    Explanations

    Cross and compounds

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

    instances of the word "Cross" particularly in names of organizations, locations, and products.

    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
     
    -4.06
    (
    -3.28
    .
    -3.27
    >
    -3.00
    B
    -2.89
          
    -2.84
    S
    -2.78
    '
    -2.52
    O
    -2.52
    \
    -2.52
    POSITIVE LOGITS
    erintah
    3.13
    歃
    2.97
     стоковая
    2.92
    鋮
    2.91
    ︓
    2.88
    Lithuan
    2.86
    Meik
    2.78
    龃
    2.75
    ेमाल
    2.72
     新聞
    2.72
    Activations Density 0.017%

    No Known Activations