© 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. 34-GEMMASCOPE-RES-131K
    7. 86738
    Prev
    Next
    INDEX
    Explanations

    apache license

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

    The neuron detects boilerplate Apache License header text (e.g. “Licensed under the Apache License, Version 2.0”).

    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
    ˂
    -1.09
    timg
    -1.05
    ofa
    -1.04
    tong
    -1.03
    ;
    -1.02
    ≅
    -1.00
    randi
    -0.98
     Medications
    -0.98
    %%%%%%%%%%%%
    -0.98
    Schools
    -0.97
    POSITIVE LOGITS
    動物園
    1.05
     still
    0.98
     市場
    0.95
    resizingMask
    0.90
    Colabor
    0.88
    促進
    0.86
    ૦
    0.83
    Procedimento
    0.82
    Capa
    0.82
    諺
    0.82
    Activations Density 1.017%

    No Known Activations