© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 808
    Prev
    Next
    INDEX
    Explanations

    Apple devices and apps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_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
     Dirichlet
    0.62
    ┴
    0.56
     لخ
    0.53
     "./
    0.52
     traceback
    0.52
    }})\
    0.52
    দক্ষ
    0.51
     عمان
    0.51
     tgt
    0.51
     './
    0.50
    POSITIVE LOGITS
     Xcode
    1.88
     SwiftUI
    1.87
    Xcode
    1.86
     iOS
    1.83
    iOS
    1.81
     Apple
    1.75
     iCloud
    1.73
    Apple
    1.70
    iPhone
    1.68
     iPhone
    1.64
    Activations Density 0.244%

    No Known Activations