© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 114115
    Prev
    Next
    INDEX
    Explanations

    receive a

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

    The neuron strongly activates on the verb “receive,” especially in calls-to-action or statements about getting something.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    y
    -3.00
    ي
    -2.81
    x
    -2.81
    which
    -2.75
    ar
    -2.70
    他の
    -2.70
     they
    -2.69
    й
    -2.58
    os
    -2.55
    H
    -2.47
    POSITIVE LOGITS
    谖
    3.41
    ญี่ป
    2.86
    
    2.81
    Donativos
    2.63
    CurtirCurtir
    2.59
    ﺐ
    2.58
    簠
    2.50
    絝
    2.50
    屜
    2.50
     hoher
    2.50
    Activations Density 0.035%

    No Known Activations