© 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. 48230
    Prev
    Next
    INDEX
    Explanations

    in source

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

    This neuron fires on the license‐style phrase “in source and binary forms” (i.e. the “in source” part of redistribution permissions).

    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
    gemene
    -0.85
    ܪ
    -0.81
    ăzi
    -0.76
     affordability
    -0.76
     hệ
    -0.74
     definitely
    -0.74
    建立
    -0.74
    ワー
    -0.74
     detr
    -0.71
     all
    -0.71
    POSITIVE LOGITS
    OnClick
    0.80
    Ronaldo
    0.79
     corpor
    0.78
    ┄
    0.78
     UILabel
    0.77
    compile
    0.76
     heran
    0.76
    pression
    0.76
    コマンド
    0.76
    specifier
    0.76
    Activations Density 0.010%

    No Known Activations