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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 70701
    Prev
    Next
    INDEX
    Explanations

    sorry or apologies

    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_22/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
     ओवर
    -1.00
     brioche
    -0.82
    淬
    -0.81
     церков
    -0.80
     WHEREAS
    -0.80
     dortmund
    -0.80
    Voxel
    -0.79
     complains
    -0.78
     vélo
    -0.78
    tyg
    -0.78
    POSITIVE LOGITS
     sorry
    1.50
     Sorry
    1.45
     promise
    1.36
    Sorry
    1.29
     apologe
    1.27
     apologised
    1.21
     apologize
    1.20
     apologies
    1.16
     Please
    1.12
    promise
    1.12
    Activations Density 0.058%

    No Known Activations