© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 3515
    Prev
    Next
    INDEX
    Explanations

    code keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    핞
    0.81
    氇
    0.72
    дям
    0.71
    ድግዳ
    0.70
    いますが
    0.68
     pavattati
    0.68
    プレイヤー
    0.68
    います
    0.67
     स्वचालित
    0.67
     这
    0.66
    POSITIVE LOGITS
    u
    1.32
    a
    1.18
    ar
    1.09
    ла
    1.07
    ون
    1.05
    い
    1.04
    ли
    1.02
    ı
    1.02
    ة
    1.02
    ب
    1.01
    Activations Density 0.301%

    No Known Activations