© 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. 34-GEMMASCOPE-RES-131K
    7. 118201
    Prev
    Next
    INDEX
    Explanations

    substituted isoquinolines

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

    chemical compound names and molecular structures in scientific literature.

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

    The neuron activates on numeric identifiers and their punctuation (digits, commas, hyphens) in chemical compound names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    fycat
    -0.80
    verre
    -0.76
    酸化
    -0.74
     Kig
    -0.73
    Produits
    -0.72
    DAMAGE
    -0.72
     weekdays
    -0.72
    чним
    -0.71
    loco
    -0.71
    locating
    -0.71
    POSITIVE LOGITS
     Lazar
    0.85
     thi
    0.80
     hydra
    0.80
    ваясь
    0.78
     Mann
    0.77
     hyd
    0.73
    вайтесь
    0.73
    チア
    0.72
     Hydra
    0.72
    SFX
    0.71
    Activations Density 0.159%

    No Known Activations