© 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. 192859
    Prev
    Next
    INDEX
    Explanations

    selection or choice

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

    choosing based on context

    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
    小さな
    0.54
     صغير
    0.51
     작은
    0.46
    ائد
    0.46
    smallest
    0.45
    кової
    0.44
    小さい
    0.44
    デイ
    0.44
    징
    0.43
     easiest
    0.43
    POSITIVE LOGITS
    总量
    0.49
    选择
    0.48
     Anspr
    0.48
     मिलते
    0.47
     专业
    0.46
     výbě
    0.46
     Himachal
    0.45
     wybor
    0.45
    Choose
    0.45
     Matemat
    0.44
    Activations Density 0.001%

    No Known Activations