© 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. 103102
    Prev
    Next
    INDEX
    Explanations

    orientation

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

    time, Chapters, it

    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
     መስ
    0.56
    PTV
    0.51
     ボディ
    0.50
     गिव
    0.49
    蒈
    0.48
     نئی
    0.47
     නව
    0.47
    ロック
    0.46
     compromising
    0.46
    ລ
    0.46
    POSITIVE LOGITS
     falls
    0.47
    另一种
    0.46
     Falls
    0.43
     kaleidos
    0.43
     Mit
    0.42
    建議
    0.41
     viewfinder
    0.41
    建议
    0.41
    vér
    0.41
     pic
    0.40
    Activations Density 0.000%

    No Known Activations