© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25930
    Prev
    Next
    INDEX
    Explanations

    class definitions

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

    This neuron responds to code declaration lines—especially public class definitions (and their associated XML doc‐comment summary tags).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    シャレ
    -1.22
    一個人
    -1.14
    laint
    -1.14
    色んな
    -1.14
    ほとん
    -1.13
    ピッタリ
    -1.12
     ejerc
    -1.10
     crucial
    -1.10
     splendid
    -1.09
    素晴らしい
    -1.09
    POSITIVE LOGITS
    man
    1.08
    ielles
    1.06
     >=",
    1.05
    🥇
    1.04
    .
    1.04
     Park
    1.04
     Data
    1.02
     Desember
    1.02
    불
    1.01
    
    1.01
    Activations Density 0.018%

    No Known Activations