© 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. 67753
    Prev
    Next
    INDEX
    Explanations

    JavaScript controllers

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

    The neuron fires on occurrences of the word “controller,” especially in Angular-JS code where a controller is being defined or referenced.

    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
     pinpoint
    -1.09
    这种
    -0.98
    ípio
    -0.96
    甚至
    -0.95
     conhecida
    -0.90
    掉的
    -0.90
    反正
    -0.89
    '
    -0.89
     afirma
    -0.88
     dotyczące
    -0.87
    POSITIVE LOGITS
     avancer
    1.09
    aziland
    1.07
    ECTION
    1.07
    罒
    1.07
     generación
    1.05
    𓄹
    1.01
    內容簡介
    1.01
     tablette
    0.99
    ():
    0.99
    ggling
    0.99
    Activations Density 0.004%

    No Known Activations