© 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. 21402
    Prev
    Next
    INDEX
    Explanations

    ethylene and its common derivatives

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

    chemical compounds and organic molecules, particularly ethylene and related chemicals.

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

    The neuron detects mentions of unsaturated hydrocarbon names (e.g. alkenes like ethylene, propylene, butadiene, and related “-ene”/“olefin” terms).

    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
    en
    -2.69
    M
    -2.66
    in
    -2.66
    end
    -2.64
    at
    -2.61
    re
    -2.47
    S
    -2.45
    镦
    -2.44
     has
    -2.44
    c
    -2.41
    POSITIVE LOGITS
    ſelf
    2.70
     größeren
    2.19
     contratar
    2.19
    砥
    2.09
     elegantes
    2.08
     Produkten
    2.06
    三日
    2.05
     einzelnen
    1.99
     perfectos
    1.97
     encantador
    1.93
    Activations Density 0.009%

    No Known Activations