© 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. 81262
    Prev
    Next
    INDEX
    Explanations

    links and web content

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

    The neuron fires strongly on generic website boilerplate—privacy policies, legal disclaimers, content/disclaimer notices, links and related site-navigation text.

    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
     thừa
    -0.82
     edición
    -0.81
    rachtet
    -0.77
     konkrét
    -0.77
     приез
    -0.75
     bazı
    -0.74
    ведении
    -0.74
    繊
    -0.73
    籁
    -0.71
    надца
    -0.71
    POSITIVE LOGITS
     third
    1.31
     links
    1.27
     privacy
    1.16
     linking
    1.13
    Link
    1.13
     Drit
    1.11
    link
    1.06
     link
    1.05
    privacy
    0.98
     linked
    0.97
    Activations Density 0.014%

    No Known Activations