© 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. 70519
    Prev
    Next
    INDEX
    Explanations

    games, Olympics, warned, career, Optical, free, quantitation

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

    The neuron activates on the “future‐tense sporting‐event announcement” style phrasing—e.g. lines listing match times, “will be” feature games, double-headers, and competing teams.

    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
     that
    -1.29
     enggak
    -1.20
    先生の
    -1.14
     maaaring
    -1.09
     may
    -1.09
     Auftritt
    -1.05
    先生が
    -1.03
    どちらも
    -1.01
     Bildschirm
    -0.98
    личные
    -0.98
    POSITIVE LOGITS
     fick
    1.15
     فلسط
    1.12
    िज
    1.12
    њи
    1.11
    落的
    1.08
     vírus
    1.07
    বি
    1.06
    veyard
    1.06
    berra
    1.05
     Elixir
    1.05
    Activations Density 0.002%

    No Known Activations