© 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. 48409
    Prev
    Next
    INDEX
    Explanations

    polyethylene glycol (PEG)

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

    The neuron detects references to "peg" or "PEG" (polyethylene glycol) in scientific and financial 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
    .
    -3.70
    ↵↵
    -2.92
    }
    -2.91
    -
    -2.84
    7
    -2.50
     –
    -2.48
     been
    -2.47
    她
    -2.39
     alguns
    -2.27
     ${
    -2.25
    POSITIVE LOGITS
    汌
    2.64
    geſ
    2.59
    螄
    2.53
    ئه
    2.52
    觧
    2.50
    کتری
    2.48
    勦
    2.47
     são
    2.47
    ﭽ
    2.41
     絲
    2.38
    Activations Density 0.005%

    No Known Activations