© 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. 10-GEMMASCOPE-RES-131K
    7. 67867
    Prev
    Next
    INDEX
    Explanations

    dimethyl chemical compounds

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

    The neuron identifies chemical compounds with "dimethyl" in their name, particularly in scientific and chemical 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
     \&
    -3.16
    ↵↵
    -2.92
    ↵
    -2.72
     to
    -2.41
     "
    -2.39
     \
    -2.33
     birkaç
    -2.28
    gezogen
    -2.19
     and
    -2.13
    原神
    -2.13
    POSITIVE LOGITS
    as
    3.58
    The
    2.89
    They
    2.81
    having
    2.67
    e
    2.64
    Other
    2.63
    To
    2.55
    ጺ
    2.55
     置物
    2.53
    ar
    2.52
    Activations Density 0.002%

    No Known Activations