© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130160
    Prev
    Next
    INDEX
    Explanations

    chemical and biological compounds

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

    scientific and biochemical terminology, particularly related to enzymes, compounds, and molecular structures.

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

    The neuron activates on specialized technical/scientific terminology (e.g. chemical names, biological compounds, instrumentation descriptors) in a document.

    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
    Sortie
    -1.58
    蟜
    -1.57
    莜
    -1.56
    Huile
    -1.55
     miſ
    -1.54
    vriende
    -1.52
     Tamanho
    -1.51
     prét
    -1.50
    Ouverture
    -1.50
    avond
    -1.47
    POSITIVE LOGITS
     enable
    1.58
     enabled
    1.52
     i
    1.50
     тот
    1.43
     that
    1.42
    x
    1.39
     helped
    1.34
     one
    1.30
           
    1.30
    )
    1.30
    Activations Density 0.316%

    No Known Activations