© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90819
    Prev
    Next
    INDEX
    Explanations

    midday and afternoon times

    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
    8
    -1.43
    9
    -1.38
    6
    -1.08
    7
    -1.07
     eighties
    -1.00
     ninety
    -0.97
     ۸
    -0.95
    七八
    -0.95
     ۹
    -0.94
     NINE
    -0.90
    POSITIVE LOGITS
     noon
    2.95
     Noon
    2.31
    noon
    1.93
    Noon
    1.86
     midday
    1.56
    NOON
    1.46
     lunchtime
    1.39
    中午
    1.34
    🕛
    1.20
     lunch
    1.17
    Activations Density 0.043%

    No Known Activations