© 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. 98839
    Prev
    Next
    INDEX
    Explanations

    chemical and biological processes

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

    This neuron identifies scientific terms related to chemical and biological processes and transformations, particularly focusing on terms like "transformation", "modification", "precipitation", and various chemical reactions ending in "-ation".

    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
    INFORMATION
    -0.89
     emporter
    -0.85
     Reykjavik
    -0.85
    힝
    -0.84
     gefüllt
    -0.83
    Mechanisms
    -0.83
     NYT
    -0.82
    rücken
    -0.82
     flexibilidad
    -0.82
     Mademoiselle
    -0.81
    POSITIVE LOGITS
     of
    3.20
     procedure
    1.30
     procedures
    1.25
     strategy
    1.21
     conditions
    1.12
     protocol
    1.09
     experiments
    1.07
     strategies
    1.06
     with
    1.05
     by
    1.02
    Activations Density 0.367%

    No Known Activations