© 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. 10-GEMMASCOPE-RES-131K
    7. 41276
    Prev
    Next
    INDEX
    Explanations

    grand hotel halls

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

    The neuron fires on occurrences of “grand” (or “Grand”) and its immediately following term in common multiword expressions (e.g. grand tourer, grand hotel, grand opening, grand total, Grand Jury, Grand Duchy).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    躂
    -2.38
    也可
    -2.16
    懨
    -1.96
     говорил
    -1.88
    boneca
    -1.88
     rivista
    -1.88
    也會
    -1.84
    ローブ
    -1.83
    🧏
    -1.82
     Perfon
    -1.78
    POSITIVE LOGITS
    一小
    1.88
     sorta
    1.79
    他
    1.77
    จัก
    1.73
     немного
    1.67
     of
    1.67
    一个月
    1.64
    取り
    1.59
     وت
    1.54
     strides
    1.54
    Activations Density 0.012%

    No Known Activations