© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 103017
    Prev
    Next
    INDEX
    Explanations

    morning

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

    Morning (time)

    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
    Negative Logits
    ın
    0.77
    är
    0.71
    ası
    0.67
    日は
    0.67
     ውስጥ
    0.65
     ライト
    0.64
    á
    0.64
    icie
    0.61
    ōng
    0.61
    ichting
    0.61
    POSITIVE LOGITS
    f
    0.91
    in
    0.81
    U
    0.67
    Checksum
    0.66
    h
    0.66
    b
    0.65
    𝚣
    0.65
    s
    0.64
     acclaimed
    0.62
    稳定的
    0.62
    Activations Density 0.052%

    No Known Activations