© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33546
    Prev
    Next
    INDEX
    Explanations

    context variable `ctx`

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

    The neuron detects occurrences of the identifier “ctx” (the common abbreviation for a context object).

    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
    Ꭳ
    -2.84
    नलोड
    -2.77
    that
    -2.44
     That
    -2.34
    𖥧
    -2.22
     []
    -2.22
    इटम
    -2.16
    仂
    -2.11
     '../../../../
    -2.11
    
    -2.05
    POSITIVE LOGITS
    s
    3.08
    솝
    2.80
    \
    2.53
    к
    2.50
    をしています
    2.45
    лся
    2.36
    癭
    2.36
    at
    2.36
    y
    2.34
    鉿
    2.27
    Activations Density 0.001%

    No Known Activations