© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12842
    Prev
    Next
    INDEX
    Explanations

    either or

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

    The neuron fires on domain‐specific technical terms and code identifiers (e.g. function names like WndProc, jargon like “arranged” in specs, punctuation in code samples).

    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
     and
    -1.23
    тический
    -1.05
     psychi
    -1.00
    筧
    -1.00
    และ
    -0.99
     Septembre
    -0.99
    萩
    -0.96
    !
    
    -0.96
     perpé
    -0.95
     maxime
    -0.93
    POSITIVE LOGITS
     or
    2.75
     either
    2.17
    いずれ
    1.91
     либо
    1.84
     depending
    1.66
     или
    1.65
     Either
    1.61
    或者是
    1.54
     hoặc
    1.54
     respectively
    1.52
    Activations Density 0.142%

    No Known Activations