© 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. 34-GEMMASCOPE-RES-131K
    7. 2587
    Prev
    Next
    INDEX
    Explanations

    alcohol and organic synthesis

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

    chemical compounds and molecular structures in scientific text.

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

    This neuron detects systematic chemical compound names (IUPAC‐style names with numbers, hyphens, and multi‐part words).

    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
    ight
    -0.88
     Phono
    -0.83
    ZONE
    -0.77
    вите
    -0.75
    Debugging
    -0.75
    atians
    -0.72
     owls
    -0.71
    传承
    -0.70
     anthracite
    -0.69
    wisata
    -0.69
    POSITIVE LOGITS
     gas
    0.95
    diol
    0.85
     Gas
    0.84
     sulfon
    0.80
    ulfon
    0.79
     Allen
    0.79
    Gas
    0.77
     Alison
    0.76
     Receive
    0.74
    oxygen
    0.74
    Activations Density 0.091%

    No Known Activations