© 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. 34-GEMMASCOPE-RES-131K
    7. 47079
    Prev
    Next
    INDEX
    Explanations

    company names ending in Ltd or Limited

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     dessa
    -0.85
     basit
    -0.84
     CORP
    -0.81
     Harbor
    -0.80
     recognized
    -0.77
     gekennzeichnet
    -0.75
    Harbor
    -0.74
     CSIRO
    -0.73
    ūsu
    -0.72
     अध्य
    -0.72
    POSITIVE LOGITS
     Ltd
    2.11
     Limited
    1.79
    Limited
    1.54
     who
    1.37
    Ltd
    1.35
    limited
    1.26
     limited
    1.25
     LIMITED
    1.24
     ltd
    1.21
    ltd
    1.07
    Activations Density 0.055%

    No Known Activations