© 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. 22-GEMMASCOPE-RES-131K
    4. 476
    Prev
    Next
    INDEX
    Explanations

    view, News, Read

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

    The neuron flags bits of UI or navigation/truncation scaffolding (ellipses, “view,” “more,” pagination numbers, etc.) rather than actual content.

    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
    क्षा
    -0.92
    Пото
    -0.91
    Сейчас
    -0.88
    スズキ
    -0.86
    chehen
    -0.85
    🔀
    -0.84
    獪
    -0.84
    ului
    -0.83
     daisies
    -0.82
    올
    -0.81
    POSITIVE LOGITS
     and
    0.88
    фикация
    0.84
    dey
    0.81
    系的
    0.81
     Ministers
    0.78
    '><
    0.78
     continúas
    0.77
    շ
    0.77
    Lire
    0.77
    rial
    0.77
    Activations Density 0.010%

    No Known Activations