© 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. 22-GEMMASCOPE-RES-131K
    7. 28218
    Prev
    Next
    INDEX
    Explanations

    alkylaminesorganasilicates

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

    chemical compound terms and elements, particularly related to alkyl groups and metals.

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

    This neuron detects mentions of chemical substituent groups and related moieties (e.g., alkyl, acyl, organo, poly-, diacyl, etc.) in 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_22/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
    是一個
    -0.93
     ferait
    -0.90
     Β
    -0.89
     article
    -0.88
    能让
    -0.88
     déplacements
    -0.86
    两个人
    -0.84
    institutions
    -0.84
     появления
    -0.83
     様子
    -0.82
    POSITIVE LOGITS
     such
    1.07
     specific
    1.00
    Vì
    0.93
     jeweiligen
    0.91
     different
    0.91
     especially
    0.91
     painless
    0.90
    롱
    0.90
    GRES
    0.90
     özellikle
    0.87
    Activations Density 0.210%

    No Known Activations