© 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. 212041
    Prev
    Next
    INDEX
    Explanations

    the days past first time

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

    the before specific dates

    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
     A
    0.69
     The
    0.59
     What
    0.57
     These
    0.55
    uhu
    0.53
     Someone
    0.52
    ំន
    0.51
     Significant
    0.50
     দ্য
    0.50
    INK
    0.49
    POSITIVE LOGITS
     οποίο
    0.52
     //<
    0.52
     концу
    0.50
     way
    0.50
    ン
    0.50
    時
    0.48
    ophylline
    0.48
    時候
    0.48
     경우에는
    0.47
    置いて
    0.47
    Activations Density 0.197%

    No Known Activations