© 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. 178362
    Prev
    Next
    INDEX
    Explanations

    shady types, nails, need

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

    following ordinal numbers

    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
     sayısı
    0.52
    ین
    0.48
    数を
    0.45
    数は
    0.44
    이어
    0.44
    していますが
    0.43
    합
    0.42
     Corte
    0.42
    ات
    0.41
    도
    0.41
    POSITIVE LOGITS
     المناطق
    0.49
    stethoscope
    0.44
     τρί
    0.43
    Bathroom
    0.42
    bathroom
    0.42
    Albums
    0.41
     photoelectric
    0.41
     женой
    0.40
     bathroom
    0.40
    auction
    0.39
    Activations Density 0.001%

    No Known Activations