© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 97754
    Prev
    Next
    INDEX
    Explanations

    Microcirculatory, Constantinos

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

    code and programming-related content, particularly looking for programming languages, libraries, and technical terminology.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects programming-style tokens—especially library or API names, method 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
    噎
    -0.71
    tetés
    -0.70
     oppose
    -0.70
     informou
    -0.69
    完成です
    -0.69
    oppa
    -0.69
     muzy
    -0.68
     unauthorized
    -0.66
    蹶
    -0.66
    地區
    -0.65
    POSITIVE LOGITS
     Struct
    0.84
    SplashScreen
    0.79
    格子
    0.75
     JTable
    0.74
     کری
    0.74
     LING
    0.73
     grille
    0.72
    👝
    0.72
    Struct
    0.72
     nô
    0.72
    Activations Density 0.020%

    No Known Activations