© 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. 34-GEMMASCOPE-RES-131K
    4. 422
    Prev
    Next
    INDEX
    Explanations

    AngularJS directives

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

    This neuron detects occurrences of the letter sequence “ng” (or “Ng”) within tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ègre
    -0.68
    ী
    -0.68
    motion
    -0.68
     motion
    -0.67
     годы
    -0.66
     Bakery
    -0.66
    국
    -0.66
    pds
    -0.66
    queues
    -0.66
    こんな感じ
    -0.66
    POSITIVE LOGITS
     ng
    1.27
     NG
    1.23
    Ng
    1.20
     Ng
    1.13
    NG
    1.09
     NGC
    0.93
    Reducing
    0.88
     Nga
    0.84
    NGL
    0.84
    Meanwhile
    0.82
    Activations Density 0.036%

    No Known Activations