© 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. 34-GEMMASCOPE-RES-131K
    7. 2382
    Prev
    Next
    INDEX
    Explanations

    open connection, subject to

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

    The neuron fires on code identifiers and other capitalized tokens (e.g. class/method/property names written in CamelCase or TitleCase).

    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
    Dtor
    -0.73
     PBX
    -0.72
    Ago
    -0.72
     يون
    -0.71
    ivi
    -0.71
    кт
    -0.69
     estou
    -0.69
     scaly
    -0.69
     изготовления
    -0.68
    Release
    -0.68
    POSITIVE LOGITS
    OURI
    0.66
    ()->
    0.66
    utzung
    0.62
    Полу
    0.62
    行程
    0.62
    herjee
    0.61
    conectar
    0.61
    пари
    0.60
    VDD
    0.59
    browse
    0.59
    Activations Density 0.076%

    No Known Activations