© 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. 66151
    Prev
    Next
    INDEX
    Explanations

    service names

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

    The neuron fires on programming‐language tokens—especially class or constant names, API calls, and other code identifiers.

    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
    Minerals
    -0.73
    TECN
    -0.71
    chures
    -0.71
    法的
    -0.71
    古墳
    -0.70
    赈
    -0.69
    ريح
    -0.69
    ҩ
    -0.69
    动了
    -0.69
     动
    -0.69
    POSITIVE LOGITS
     services
    2.02
     UserService
    1.68
    UserService
    1.66
    OrderService
    1.60
     service
    1.59
     servizi
    1.55
     AuthService
    1.48
     servicios
    1.47
    userService
    1.46
     خدمات
    1.45
    Activations Density 0.081%

    No Known Activations