© 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. 223146
    Prev
    Next
    INDEX
    Explanations

    afternoon, lunchtime, noon, PM

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

    lunchtime

    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
     nightly
    0.51
    睡眠
    0.46
     semanas
    0.45
     সপ্তাহে
    0.45
     đèn
    0.44
    灯
    0.41
    两年
    0.41
    毎週
    0.41
     preseason
    0.40
    Weeks
    0.40
    POSITIVE LOGITS
    中午
    1.38
     afternoon
    1.34
     दोपहर
    1.29
     midday
    1.28
    下午
    1.25
     Afternoon
    1.23
     pomeriggio
    1.17
     lunchtime
    1.15
     দুপুর
    1.14
     Lunch
    1.11
    Activations Density 0.129%

    No Known Activations