© 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. 73818
    Prev
    Next
    INDEX
    Explanations

    HTML head elements

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

    The neuron fires on directory or file‐path segments (e.g. URL/path literals) in HTML and script tags.

    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
     its
    -1.79
     who
    -1.34
     about
    -1.31
     over
    -1.26
     on
    -1.21
     that
    -1.20
    ingin
    -1.20
     his
    -1.15
     it
    -1.12
    setLayoutManager
    -1.12
    POSITIVE LOGITS
     morire
    1.46
    توضیحات
    1.42
    商品説明
    1.32
     parteci
    1.30
     rimanere
    1.27
    ítico
    1.26
    معرفی
    1.25
    День
    1.20
    دانلود
    1.19
    Themen
    1.19
    Activations Density 0.002%

    No Known Activations