© 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. 62718
    Prev
    Next
    INDEX
    Explanations

    pay for something

    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
    Not in Any Lists

    No Comments

    Negative Logits
    捗
    -0.95
    名叫
    -0.90
    tigten
    -0.85
     updating
    -0.85
     アイテム
    -0.84
    めんなさい
    -0.84
    IOUtils
    -0.82
     étudier
    -0.81
     佐
    -0.80
    챌
    -0.79
    POSITIVE LOGITS
     for
    1.89
     attention
    1.77
     homage
    1.59
     tribute
    1.48
     Attention
    1.26
    attention
    1.16
    Attention
    1.13
     someone
    1.07
     perhatian
    1.05
     somebody
    1.04
    Activations Density 0.012%

    No Known Activations