© 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. 34-GEMMASCOPE-RES-131K
    7. 47156
    Prev
    Next
    INDEX
    Explanations

    names starting with Billy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ers
    -0.85
    ere
    -0.82
    wargs
    -0.79
    Loki
    -0.79
    ERT
    -0.77
     Gupta
    -0.77
    Poznám
    -0.75
    Nairobi
    -0.74
    !"
    -0.74
    левой
    -0.74
    POSITIVE LOGITS
     Goat
    1.15
    goat
    1.00
     goat
    0.96
    𝐔
    0.96
     Goats
    0.94
    joel
    0.93
     Billy
    0.91
    Joe
    0.91
     Idol
    0.89
     Liar
    0.89
    Activations Density 0.007%

    No Known Activations