© 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. 22-GEMMASCOPE-RES-131K
    7. 67752
    Prev
    Next
    INDEX
    Explanations

    programming code and function calls

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

    The neuron is strongly triggered by array‐assignment syntax (brackets “[]” and the surrounding assignment operators) in code.

    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
    negara
    -1.04
     corporativa
    -0.93
     jeweils
    -0.93
    greenrobot
    -0.88
    Šaltiniai
    -0.85
     각
    -0.84
     ketentuan
    -0.84
     gleichen
    -0.84
    hts
    -0.82
     telefónica
    -0.82
    POSITIVE LOGITS
    ウンサー
    0.97
    PILE
    0.93
     because
    0.91
     потому
    0.89
    chọn
    0.88
     समु
    0.86
    ሥ
    0.85
     megt
    0.85
    دارد
    0.84
     people
    0.84
    Activations Density 0.004%

    No Known Activations