© 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. 68730
    Prev
    Next
    INDEX
    Explanations

    accessing properties of 'this'

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

    The neuron fires on numeric literal tokens in source code.

    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
    larınız
    -2.22
     Anſ
    -2.09
     THOSE
    -2.09
    
    -2.06
    increased
    -2.00
     unbelievably
    -1.98
     dôle
    -1.97
     focuses
    -1.96
    those
    -1.93
     incluye
    -1.91
    POSITIVE LOGITS
     new
    2.34
     first
    2.28
     two
    2.27
     three
    2.25
     more
    2.08
     only
    2.00
     centavos
    1.96
    というわけで
    1.95
    if
    1.92
    余談
    1.90
    Activations Density 0.008%

    No Known Activations