© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78734
    Prev
    Next
    INDEX
    Explanations

    future dates and quantities

    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
    Not in Any Lists

    No Comments

    Negative Logits
    当时
    -0.96
     erste
    -0.93
    それ
    -0.93
     Show
    -0.91
    le
    -0.91
     damals
    -0.88
    ímetro
    -0.85
     Multiple
    -0.84
    actéris
    -0.83
     trước
    -0.82
    POSITIVE LOGITS
     few
    2.84
     quelques
    2.28
     vài
    2.17
    few
    1.93
     couple
    1.90
    Few
    1.80
    Quelques
    1.78
     چند
    1.74
     néhány
    1.71
     about
    1.66
    Activations Density 0.027%

    No Known Activations