© 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. 34-GEMMASCOPE-RES-131K
    7. 48685
    Prev
    Next
    INDEX
    Explanations

    impurities and contaminants

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

    phrases describing contaminants or impurities in substances.

    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_34/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
     undermined
    -0.80
     године
    -0.80
     EXPORT
    -0.77
     sorrows
    -0.76
    paddingTop
    -0.75
    pantalón
    -0.73
     Contractors
    -0.73
    jogador
    -0.73
     białym
    -0.73
     Algorithms
    -0.72
    POSITIVE LOGITS
     impurities
    2.98
     contaminants
    2.30
     impurity
    2.28
     contamin
    2.02
     contamination
    1.91
     приме
    1.84
     trace
    1.81
     contaminant
    1.75
     tạp
    1.73
    conta
    1.69
    Activations Density 0.116%

    No Known Activations