© 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. 22-GEMMASCOPE-RES-131K
    7. 14812
    Prev
    Next
    INDEX
    Explanations

    user queries and instructions

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

    This neuron detects occurrences of the event‐handler parameter named “e” (the EventArgs variable) in method signatures.

    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
     to
    -1.45
    NTSTATUS
    -1.14
     ۱۱
    -1.13
    被告
    -1.06
    helo
    -1.06
     For
    -1.05
     personaggio
    -1.05
     Each
    -1.03
     From
    -1.02
     abgerufen
    -1.00
    POSITIVE LOGITS
    habited
    1.28
     DOMINGO
    1.18
     rimu
    1.12
    ቼ
    1.11
    仍在
    1.06
     applau
    1.05
     débris
    1.05
    人で
    1.05
     scarpe
    1.05
    ívar
    1.05
    Activations Density 0.001%

    No Known Activations