© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33688
    Prev
    Next
    INDEX
    Explanations

    SAP programming and terminology

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

    The neuron fires on chunks of technical code or code‐like identifiers (e.g. SAP/ABAP field names, module names, uppercase tokens, and other programming syntax).

    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
    qJ
    -0.73
     Watcher
    -0.70
     słucha
    -0.70
     Immobili
    -0.68
     ESTR
    -0.67
    周泽
    -0.66
    積極
    -0.66
    ੰ
    -0.64
    DataModel
    -0.64
     brawl
    -0.64
    POSITIVE LOGITS
     Exit
    0.96
    EXIT
    0.89
     exit
    0.88
    Exit
    0.88
    asikan
    0.86
     exits
    0.85
    Expressions
    0.85
     PCR
    0.85
     MAT
    0.81
    EQU
    0.81
    Activations Density 0.024%

    No Known Activations