© 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. 83881
    Prev
    Next
    INDEX
    Explanations

    cort as prefix

    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
    }$
    -3.00
    筇
    -2.31
    re
    -2.25
    neling
    -2.25
    FORCEMENT
    -2.23
    鲠
    -2.20
    son
    -2.19
     Чтобы
    -2.14
    mit
    -2.11
    ть
    -2.11
    POSITIVE LOGITS
    jaqueta
    3.06
    
    2.83
    晙
    2.66
    т
    2.66
    摃
    2.59
    焄
    2.44
    懨
    2.44
    霂
    2.38
    我可以
    2.34
     maternelle
    2.34
    Activations Density 0.006%

    No Known Activations