© 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. 9736
    Prev
    Next
    INDEX
    Explanations

    people and things displaced

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

    The neuron fires on terms expressing displacement or uprooting (e.g. “displaced,” “uprooted”).

    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
     laquelle
    -2.16
    ╹
    -2.13
    ｕ
    -2.02
    ⤴
    -1.91
    設置
    -1.87
    The
    -1.87
    There
    -1.81
    ✕
    -1.80
     gäller
    -1.80
    怍
    -1.80
    POSITIVE LOGITS
    ’
    3.00
     of
    2.41
    ’:
    2.27
    ’，
    2.06
     “
    2.06
    
    2.02
    ’).
    1.94
    ：“
    1.91
     beberapa
    1.89
     berbagai
    1.86
    Activations Density 0.004%

    No Known Activations