© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70802
    Prev
    Next
    INDEX
    Explanations

    colliery, buried, interments

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

    The neuron activates on words relating to burial or internment (e.g. “interments,” “internment,” “burial”).

    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
    N
    -2.47
    C
    -2.34
    
    -2.30
    精神
    -2.13
    และ
    -2.13
     }).
    -2.11
    A
    -2.09
     '-':
    -2.05
    %(
    -2.00
    geten
    -2.00
    POSITIVE LOGITS
    欵
    2.52
    
    2.27
    灕
    2.16
    ates
    2.08
     envió
    2.05
     ofreció
    2.03
    哔
    2.02
     verbess
    1.99
    話は
    1.98
     acompaña
    1.98
    Activations Density 0.003%

    No Known Activations