© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 59270
    Prev
    Next
    INDEX
    Explanations

    website related terms

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

    The neuron fires strongly on occurrences of “website” (and related “web-” tokens), i.e. when the text mentions a website or web-based service.

    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
    sizable
    -1.13
    咴
    -1.12
     emprego
    -1.11
     estudante
    -1.08
     reconhecimento
    -1.05
    écrivain
    -1.05
     fashioned
    -1.04
    鷥
    -1.03
    animaux
    -1.02
    1
    -1.02
    POSITIVE LOGITS
     oficial
    1.24
     visitors
    1.23
    ㄷ
    1.21
     URL
    1.16
    閲覧
    1.16
    🎶
    1.15
     SITE
    1.15
    建设
    1.11
    Site
    1.09
     americano
    1.09
    Activations Density 0.046%

    No Known Activations