© 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. 53921
    Prev
    Next
    INDEX
    Explanations

    press release services

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

    The neuron is spot­ting wire‐service dateline tokens and source tags (e.g. “--(”, “Marketwire”, “Business Wire”, “PRWEB”, “Sports Network”).

    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
     Befehl
    -0.73
    馭
    -0.71
    Открыть
    -0.71
    Dee
    -0.69
    vallen
    -0.67
    ๗
    -0.67
    tagHelper
    -0.67
    laser
    -0.66
    Glen
    -0.66
    Fresh
    -0.66
    POSITIVE LOGITS
     teaser
    0.93
    memorial
    0.78
     happiness
    0.77
     görüntüleri
    0.76
     atrás
    0.72
     offrent
    0.72
    Pageable
    0.72
     толкова
    0.71
    anzeigen
    0.71
    cope
    0.71
    Activations Density 0.027%

    No Known Activations