© 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. 68594
    Prev
    Next
    INDEX
    Explanations

    conjunctions and relative clauses

    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
    9
    -1.56
     этом
    -1.52
    ")
    -1.46
     contactez
    -1.44
     случи
    -1.41
     также
    -1.39
     banyo
    -1.39
    ]
    -1.39
     выборе
    -1.38
    )
    -1.38
    POSITIVE LOGITS
    ,
    2.02
    僥
    1.70
    咴
    1.60
    ჱ
    1.58
     Хотя
    1.55
    𐐀
    1.53
    Ⴀ
    1.51
    を使用した
    1.48
    ньому
    1.47
     they
    1.46
    Activations Density 0.019%

    No Known Activations