© 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. 104433
    Prev
    Next
    INDEX
    Explanations

    disulfide bonds and colorless compounds

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

    scientific/chemical terms, particularly those describing properties like "colorless," "disulfide," and "hepatocellular."

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron specifically detects the adjective “colorless” when it appears in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    氿
    -2.61
    嵛
    -2.59
    鳙
    -2.58
    cinoma
    -2.53
     больших
    -2.39
    嚶
    -2.36
     detaylı
    -2.36
    llion
    -2.34
    鲩
    -2.31
    剮
    -2.30
    POSITIVE LOGITS
    on
    2.86
    1
    2.81
    an
    2.81
    ",
    2.77
    this
    2.69
    *
    2.64
    there
    2.63
    .,
    2.59
     was
    2.42
    at
    2.39
    Activations Density 0.020%

    No Known Activations