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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 515
    Prev
    Next
    INDEX
    Explanations

    week and weekend

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_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
     оболо
    1.01
    Horizontal
    0.83
    √
    0.80
     tamaños
    0.80
     linhas
    0.79
     inplace
    0.77
    IZONTAL
    0.77
    bigoplus
    0.77
     imó
    0.76
    ∞</
    0.76
    POSITIVE LOGITS
     weekend
    2.54
     afternoon
    2.32
    weekend
    2.24
     weekends
    2.23
     evening
    2.18
     week
    2.18
     morning
    2.18
     afternoons
    2.14
     weekday
    2.13
     mornings
    2.09
    Activations Density 6.283%

    No Known Activations