© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 10789
    Prev
    Next
    INDEX
    Explanations

    directions and travel paths

    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_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ைட்
    1.02
     பின்பற்ற
    0.99
     ಮಾಹಿತ
    0.98
     まとめ
    0.97
    <unused26>
    0.96
    𝗈
    0.95
    eseorang
    0.93
    ቒ
    0.92
    <unused20>
    0.91
     راجس
    0.91
    POSITIVE LOGITS
     westward
    1.33
     southward
    1.31
     northward
    1.28
     eastward
    1.16
     west
    1.12
     north
    1.09
     three
    1.05
     route
    1.04
     path
    1.02
     meandering
    1.02
    Activations Density 0.204%

    No Known Activations