© 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. 93232
    Prev
    Next
    INDEX
    Explanations

    physics and chemistry concepts

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

    physical properties and measurements in scientific contexts like electric fields, magnetic properties, and surface phenomena.

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

    This neuron responds to key technical or scientific content words—specialized nouns and terminology typical of scientific abstracts.

    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
    などは
    -1.96
    鶿
    -1.88
    などが
    -1.77
    が
    -1.73
     spann
    -1.70
     charmant
    -1.70
    粜
    -1.65
     unbelievably
    -1.65
    など
    -1.64
    
    -1.62
    POSITIVE LOGITS
     and
    2.22
     Before
    1.77
     one
    1.70
     epitom
    1.59
     it
    1.58
     utterly
    1.56
     overtly
    1.55
     Shortly
    1.52
     invigor
    1.52
     or
    1.51
    Activations Density 0.380%

    No Known Activations