© 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. 106834
    Prev
    Next
    INDEX
    Explanations

    approximately, ≈, approx, about

    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
     retir
    -0.83
    冽
    -0.80
     disser
    -0.78
     toques
    -0.77
     preta
    -0.77
    orku
    -0.77
     communities
    -0.74
     Brasília
    -0.73
     peman
    -0.71
     profesion
    -0.71
    POSITIVE LOGITS
     approximately
    2.75
     ≈
    2.75
    approx
    2.75
     about
    2.53
    ≈
    2.47
     roughly
    2.38
     approx
    2.33
    approximately
    2.23
     примерно
    2.23
    約
    2.20
    Activations Density 0.015%

    No Known Activations