© 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. 84580
    Prev
    Next
    INDEX
    Explanations

    instructional phrases

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

    The neuron fires on website “meta” text—UI prompts and instructions around commenting, registration, and community guidelines.

    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
     so
    -1.16
     because
    -1.01
     on
    -0.94
     four
    -0.92
     incessant
    -0.89
     extensive
    -0.88
     reliable
    -0.88
    欧阳
    -0.88
     avoiding
    -0.88
     usually
    -0.87
    POSITIVE LOGITS
     filmu
    1.12
    sorry
    1.09
     %{
    1.06
    "]}
    1.05
    XHR
    1.05
    {*
    1.02
     našich
    1.00
    .},
    1.00
    AntiForgery
    1.00
    OPS
    0.99
    Activations Density 0.384%

    No Known Activations