© 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. 108540
    Prev
    Next
    INDEX
    Explanations

    stack pointer, bankroll, mutation

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

    This neuron detects assembly language and low-level programming concepts like stack pointers, registers, and memory allocation.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    arif
    -0.76
     FAVOR
    -0.75
    Andrei
    -0.74
     Boring
    -0.71
     murs
    -0.71
     ав
    -0.70
    Boarding
    -0.69
    Ayrıca
    -0.69
     Schein
    -0.68
    ƽ
    -0.68
    POSITIVE LOGITS
     stack
    2.34
     stacks
    2.19
    stack
    1.97
     Stack
    1.95
    STACK
    1.95
    Stack
    1.91
     STACK
    1.88
    stacks
    1.74
    StackSize
    1.73
     Stacks
    1.60
    Activations Density 0.042%

    No Known Activations