© 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. 22717
    Prev
    Next
    INDEX
    Explanations

    therefore followed by a consequence

    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
    </b>
    -3.59
    ?"
    -3.23
     From
    -2.95
     Когда
    -2.38
     Now
    -2.33
    毉
    -2.28
     '
    -2.23
    ？」
    -2.20
     Для
    -2.20
     We
    -2.14
    POSITIVE LOGITS
    肏
    2.88
    酲
    2.80
    珢
    2.72
    鲧
    2.72
    圌
    2.67
    </h3>
    2.56
     ſou
    2.48
    谂
    2.47
    髏
    2.47
    ل
    2.47
    Activations Density 0.012%

    No Known Activations