© 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. 10-GEMMASCOPE-RES-131K
    7. 42448
    Prev
    Next
    INDEX
    Explanations

    authorship attribution

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

    The neuron flags words and forms related to authorship (e.g. author, authored, authoring).

    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
     orice
    -2.25
    鲞
    -2.17
     {
    -2.16
    琑
    -2.05
    ￬
    -2.03
    泚
    -1.98
    joyed
    -1.98
    🗿
    -1.95
    蚡
    -1.88
    ”
    -1.86
    POSITIVE LOGITS
    ↵
    2.39
    ᨆ
    2.14
    現貨
    2.06
    Ꮉ
    2.02
    excellents
    2.00
    l
    2.00
    夘
    1.99
     手作り
    1.98
    ဴ
    1.98
    المشار
    1.97
    Activations Density 0.009%

    No Known Activations