© 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. 72045
    Prev
    Next
    INDEX
    Explanations

    sports league context

    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_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
     but
    -2.75
    臯
    -2.05
    1
    -2.02
    ⚣
    -1.97
    艄
    -1.92
    汭
    -1.89
    诳
    -1.81
    鹩
    -1.80
    餿
    -1.75
    就不会
    -1.73
    POSITIVE LOGITS
    是啊
    2.11
    '
    2.08
    _
    1.96
    :
    1.95
    )
    1.90
     kemudian
    1.89
     melap
    1.88
    可以
    1.84
     siguen
    1.81
     ihe
    1.81
    Activations Density 0.013%

    No Known Activations