© 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. 58140
    Prev
    Next
    INDEX
    Explanations

    hydrocarbon chains and structures

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

    chemical compound names, molecular structures, and technical chemistry terminology.

    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_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
     oxygen
    -0.94
     phenol
    -0.86
    ámico
    -0.85
     polar
    -0.85
     alcohol
    -0.82
    phenol
    -0.82
    esters
    -0.79
    oxygen
    -0.78
     алкого
    -0.77
    Alcohol
    -0.76
    POSITIVE LOGITS
     hydrocarbons
    1.07
     propane
    1.01
     hydrocarbon
    0.97
     paraffin
    0.94
     petroleum
    0.91
    烷
    0.90
     pent
    0.89
     alkyl
    0.85
     Gasoline
    0.85
     gasoline
    0.84
    Activations Density 0.071%

    No Known Activations