© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101314
    Prev
    Next
    INDEX
    Explanations

    water and hydrogen peroxide

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

    chemical formulas for water and hydrogen peroxide (H2O and H2O2).

    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
     has
    -2.39
    Even
    -2.14
    琑
    -2.13
    s
    -2.08
    ’
    -2.08
    );
    -2.06
    just
    -2.02
    );
    -2.00
    is
    -1.97
    )’
    -1.95
    POSITIVE LOGITS
    읖
    1.98
     quintessential
    1.97
     ursprünglich
    1.89
     первая
    1.88
    眥
    1.87
    
    1.84
    
    1.80
    ໊
    1.80
     одна
    1.76
     самая
    1.74
    Activations Density 0.005%

    No Known Activations