© 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. 127570
    Prev
    Next
    INDEX
    Explanations

    detecting "new" followed by entities

    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
    是最
    -1.97
    "
    -1.93
    </strong>
    -1.75
    ⟝
    -1.75
    <bos>
    -1.71
    髣
    -1.70
    -
    -1.66
    </em>
    -1.66
    讫
    -1.63
      
    -1.60
    POSITIVE LOGITS
    新的
    2.33
    new
    2.14
    慜
    2.11
     personalizar
    2.09
     new
    2.08
    あまり
    2.05
    躥
    1.98
    珖
    1.92
     появилась
    1.84
    comers
    1.82
    Activations Density 0.161%

    No Known Activations