© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71526
    Prev
    Next
    INDEX
    Explanations

    surfactant and wildfires

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

    terms related to surfactants and wildfires.

    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
    でも
    -3.03
     -
    -3.00
    They
    -2.80
    However
    -2.73
     \
    -2.69
    –
    -2.69
    {
    -2.66
     
    -2.64
    This
    -2.59
     Then
    -2.55
    POSITIVE LOGITS
    塒
    3.23
    梣
    3.00
    圌
    2.91
    蔸
    2.83
    
    2.73
    鋌
    2.70
    gucig
    2.58
    ſam
    2.50
    phans
    2.50
    electricity
    2.48
    Activations Density 0.011%

    No Known Activations