© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5243
    Prev
    Next
    INDEX
    Explanations

    executed directly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    জনকে
    1.00
    re
    0.88
    isał
    0.83
     것을
    0.83
     decirlo
    0.81
    べく
    0.81
     اسمه
    0.81
    を
    0.81
    ことを
    0.80
     il
    0.80
    POSITIVE LOGITS
    <unused283>
    1.38
    <unused264>
    1.31
    ൯
    1.24
    <unused282>
    1.23
    বৃন্দ
    1.22
    shen
    1.21
     patham
    1.20
    <unused353>
    1.20
    <unused210>
    1.20
    <unused436>
    1.19
    Activations Density 0.043%

    No Known Activations