© 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. 69287
    Prev
    Next
    INDEX
    Explanations

    financial and medical deficits

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

    The neuron activates for the word "deficit" or "deficits", particularly in academic or medical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    扨
    -2.70
    cras
    -2.52
    ᵴ
    -2.47
    刧
    -2.47
     Теперь
    -2.47
    彞
    -2.39
     больших
    -2.38
    羕
    -2.38
    鹮
    -2.34
    樉
    -2.34
    POSITIVE LOGITS
     It
    2.45
    ка
    2.17
     иногда
    2.13
     vivía
    2.11
    出る
    2.05
    chengladbach
    2.02
    ⭕
    2.02
     eyebrow
    2.02
    E
    1.98
     andato
    1.95
    Activations Density 0.005%

    No Known Activations