© 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. 10-GEMMASCOPE-RES-131K
    7. 111863
    Prev
    Next
    INDEX
    Explanations

    emoticons and brackets

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

    This neuron detects uses of slicing operations in code, specifically expressions with a colon inside brackets (e.g., `L[n:]`, `stack[1:]`).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    $
    -2.94
    ing
    -2.50
    V
    -2.42
    A
    -2.34
    N
    -2.31
    J
    -2.28
    毆
    -2.20
    Z
    -2.20
    ൎ
    -2.17
    '
    -2.13
    POSITIVE LOGITS
    \|_{
    2.25
    賔
    2.25
     probablemente
    2.17
    assassin
    2.14
    ността
    2.14
     diseñ
    2.13
    ("")){
    2.05
      
    2.03
    樒
    2.02
     they
    1.97
    Activations Density 0.009%

    No Known Activations