© 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. 78053
    Prev
    Next
    INDEX
    Explanations

    superoxide anion generation

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

    scientific terms related to oxidation reactions and chemical compounds.

    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
     oxidative
    -0.91
    oxid
    -0.89
    Ted
    -0.83
     Oxid
    -0.82
    Leaders
    -0.81
    团队
    -0.75
     آزاد
    -0.74
    free
    -0.73
    Wal
    -0.73
     oxidation
    -0.73
    POSITIVE LOGITS
     Haber
    0.90
     super
    0.82
     generar
    0.82
     generate
    0.79
    гене
    0.77
    Haber
    0.74
     phag
    0.73
     sujeto
    0.72
     körül
    0.72
     Leto
    0.71
    Activations Density 0.097%

    No Known Activations