© 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. 103827
    Prev
    Next
    INDEX
    Explanations

    sentence introducing an article, story, or news

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

    The neuron fires on the word “This” when it appears in boilerplate or introductory sentences (e.g. “This is an archived article…”).

    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
    たくさんの
    -1.23
    ઃ
    -1.16
    いくつかの
    -1.08
    erunner
    -1.03
    ecco
    -1.02
    lorn
    -1.02
    ┍
    -1.02
     HUND
    -0.98
     katk
    -0.98
    こんなに
    -0.97
    POSITIVE LOGITS
     is
    2.28
     week
    1.98
     was
    1.92
     month
    1.47
     Week
    1.45
     year
    1.45
     article
    1.33
     wasn
    1.30
     happened
    1.22
     semana
    1.22
    Activations Density 0.066%

    No Known Activations