© 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. 13004
    Prev
    Next
    INDEX
    Explanations

    Before or author followed by names

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

    The neuron flags standalone metadata labels or headings (e.g. “Before,” “Author,” “Source,” etc.) in documents.

    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
     دانلود
    -1.06
     概要
    -0.94
     InputMaybe
    -0.92
    messung
    -0.91
     العنوان
    -0.84
    OLOGÍA
    -0.84
    CAI
    -0.82
    Diver
    -0.81
     Diver
    -0.81
     dwóch
    -0.81
    POSITIVE LOGITS
     Aden
    0.93
    しません
    0.92
     сім
    0.89
     án
    0.85
     aden
    0.85
     reste
    0.84
     betrachten
    0.84
    Sommaire
    0.82
    ycle
    0.82
    영어
    0.81
    Activations Density 0.007%

    No Known Activations