© 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. 176743
    Prev
    Next
    INDEX
    Explanations

    service or market descriptors

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

    respect, parsing, and specific areas

    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
     lạc
    0.52
     수익
    0.51
     Quốc
    0.47
    Ĵ
    0.47
     તેમને
    0.46
    젓
    0.46
     シルバー
    0.45
    씁
    0.45
     පේශ
    0.44
    chakra
    0.44
    POSITIVE LOGITS
    ن
    0.52
    廡
    0.51
    acterísticas
    0.50
    arium
    0.47
    الت
    0.46
     exemplar
    0.45
    م
    0.45
    vista
    0.44
    untamiento
    0.44
    éric
    0.44
    Activations Density 0.000%

    No Known Activations