© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108861
    Prev
    Next
    INDEX
    Explanations

    Active links & states

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

    This neuron selectively activates on CamelCase programming identifiers—especially class, module, or library names (e.g. ActiveModel, ActiveSupport, VirtualInputMethod).

    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
     beraber
    -0.84
     alimentaires
    -0.78
    edicated
    -0.78
     çek
    -0.76
    🫖
    -0.75
    culature
    -0.75
     ziehen
    -0.75
    系统
    -0.74
    Norfolk
    -0.73
    Somalia
    -0.73
    POSITIVE LOGITS
    Active
    0.90
     active
    0.89
     activo
    0.88
     Active
    0.84
     economica
    0.83
     актив
    0.82
     saisons
    0.79
     activa
    0.78
     akti
    0.77
    active
    0.76
    Activations Density 0.035%

    No Known Activations