© 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. 10251
    Prev
    Next
    INDEX
    Explanations

    oxime

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

    This neuron detects chemical compound names ending with "ime", especially focusing on chemical suffixes and nomenclature in scientific 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
    \
    -3.34
     It
    -3.22
    In
    -2.98
    2
    -2.86
     jährlich
    -2.83
    a
    -2.81
    </td>
    -2.75
     of
    -2.73
     ursprünglich
    -2.69
     umfang
    -2.61
    POSITIVE LOGITS
     humeur
    2.83
     accessoire
    2.83
     ſou
    2.69
     egens
    2.69
     apparence
    2.67
    麈
    2.63
     oiseau
    2.58
    ᨆ
    2.56
    ime
    2.53
     organisme
    2.53
    Activations Density 0.009%

    No Known Activations