© 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. 108703
    Prev
    Next
    INDEX
    Explanations

    collections

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

    This neuron recognizes the dot and sub‐namespace tokens in C# “using System.X” import lines.

    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
     marcó
    -1.05
     subió
    -1.02
     спросил
    -1.01
     serta
    -0.96
     several
    -0.96
    hcm
    -0.95
     continuó
    -0.94
     zanah
    -0.94
     ayudó
    -0.91
     when
    -0.90
    POSITIVE LOGITS
    Collections
    2.03
     Collections
    1.39
     collections
    1.17
     gesammelt
    1.02
    UI
    0.99
    Generic
    0.97
    त्र
    0.92
    Windows
    0.90
    angebot
    0.89
     সং
    0.87
    Activations Density 0.006%

    No Known Activations