© 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. 58083
    Prev
    Next
    INDEX
    Explanations

    exited or exiting a place or state

    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
    Negative Logits
    </h3>
    -2.66
    ”.
    -2.53
    a
    -2.50
    </strong>
    -2.45
    “
    -2.42
     
    -2.41
    _
    -2.36
    </h2>
    -2.30
    ).
    -2.23
    .
    -2.17
    POSITIVE LOGITS
    　　　　　
    2.47
    
    2.33
    歷史
    2.06
    ギュラー
    2.06
    ：@
    2.02
    柃
    2.02
    　　　　　　　
    2.00
    遊戲
    1.98
    圖
    1.98
    ᕱ
    1.96
    Activations Density 0.007%

    No Known Activations