© 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. 75497
    Prev
    Next
    INDEX
    Explanations

    authorship, attribution, or IDs

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

    The neuron signals when it sees structural markup or metadata tokens—things like comment delimiters (“//”), section dividers (“=====”), “By:”, dates, version numbers, and other formatting elements rather than ordinary prose.

    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
     كورة
    -0.81
     সম
    -0.81
     Office
    -0.81
     креп
    -0.80
    н
    -0.80
    成
    -0.80
    स
    -0.79
     Column
    -0.79
     Connect
    -0.78
    serva
    -0.78
    POSITIVE LOGITS
    ᴢ
    0.91
    Fundraising
    0.89
    PICTOGRAM
    0.88
     Pvt
    0.88
     oscuridad
    0.88
    孰
    0.87
     gué
    0.86
    Screenshots
    0.85
    Flashcards
    0.85
    omorphism
    0.84
    Activations Density 0.056%

    No Known Activations