© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42426
    Prev
    Next
    INDEX
    Explanations

    adrenaline and epinephrine

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

    This neuron identifies chemical compounds related to adrenaline/noradrenaline and other catecholamines in medical or 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
    9
    -2.97
    in
    -2.78
    ();
    -2.73
    (
    -2.69
    ´
    -2.58
    </u>
    -2.52
    」
    -2.48
    」、「
    -2.47
    4
    -2.45
     Großen
    -2.44
    POSITIVE LOGITS
    ႐
    2.55
     seleccionamos
    2.41
     isra
    2.39
    Ꮂ
    2.38
     bringe
    2.36
    蘗
    2.34
     возможность
    2.33
     水墨
    2.22
    錒
    2.22
    茕
    2.20
    Activations Density 0.014%

    No Known Activations