© 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. 6809
    Prev
    Next
    INDEX
    Explanations

    吃力不讨

    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
    ﹆
    -2.72
    ﻒ
    -2.63
    
    -2.61
    
    -2.47
    ᐠ
    -2.41
    尔斯
    -2.38
    ⸪
    -2.30
     Insets
    -2.27
    栳
    -2.25
    貽
    -2.20
    POSITIVE LOGITS
    </td>
    2.59
    ),
    2.33
    </b>
    2.28
     cáps
    2.23
     sebagainya
    2.17
    with
    2.13
    》，
    2.11
    ↵↵
    2.11
    自身
    2.09
    <td>
    2.08
    Activations Density 0.020%

    No Known Activations