© 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. 80788
    Prev
    Next
    INDEX
    Explanations

    congestion and congestive

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

    references to traffic or network congestion in various 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
    猻
    -3.09
    
    -2.58
     we
    -2.47
     appuntamento
    -2.44
     rapida
    -2.44
     esperienza
    -2.41
    The
    -2.38
    锨
    -2.36
     lousy
    -2.33
    ⇴
    -2.33
    POSITIVE LOGITS
    \
    3.47
    ↵
    3.34
    ),
    2.61
     &
    2.47
    ’
    2.39
    n
    2.30
    ⬮
    2.22
     -
    2.13
     or
    2.13
     оба
    2.09
    Activations Density 0.004%

    No Known Activations