© 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. 48062
    Prev
    Next
    INDEX
    Explanations

    questions or contests

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

    The neuron strongly activates on legal‐style section headings and boilerplate (e.g. “rules, terms and conditions,” “eligibility,” “promotion period”), essentially spotting contest or promotional fine‐print sections.

    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
     buyers
    -0.82
    öv
    -0.81
    ophen
    -0.81
    蔷
    -0.79
     Younger
    -0.79
    ไร
    -0.78
    mMap
    -0.76
     *
    -0.74
     подрост
    -0.73
     learners
    -0.73
    POSITIVE LOGITS
     prize
    1.13
    prize
    1.09
     contestant
    1.05
     winner
    1.01
     フリース
    1.00
     Sponsor
    0.96
     Sweep
    0.91
     PRIZE
    0.90
    entrant
    0.89
     contestants
    0.89
    Activations Density 0.010%

    No Known Activations