© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 2047
    Prev
    Next
    INDEX
    Explanations

    morning breakfast

    np_acts-logits-general · gemini-2.5-flash-lite

    morning and breakfast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tonight
    0.57
    夕
    0.53
    সন্ধ
    0.51
     সন্ধ্যার
    0.51
    Dinner
    0.49
     več
    0.48
    Evening
    0.45
    晩
    0.44
    Encode
    0.42
    晚
    0.41
    POSITIVE LOGITS
     morning
    1.93
     breakfast
    1.84
    morning
    1.80
     Morning
    1.77
     Breakfast
    1.77
    breakfast
    1.68
    早餐
    1.66
    Morning
    1.65
     सुबह
    1.64
    Breakfast
    1.63
    Activations Density 0.319%

    No Known Activations