© 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
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13284
    Prev
    Next
    INDEX
    Explanations

    comparison or choice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    اا
    1.19
    zäh
    1.17
     hordes
    1.16
    enemies
    1.14
    hā
    1.10
     machines
    1.08
    mith
    1.06
    kannya
    1.05
    ی
    1.05
    ക്കള്‍
    1.05
    POSITIVE LOGITS
     facilitation
    1.25
     집중
    1.21
     BID
    1.20
     เลข
    1.19
    開き
    1.19
    閡
    1.18
     प्रहरी
    1.18
     徐
    1.17
    esian
    1.16
    岖
    1.16
    Activations Density 0.000%

    No Known Activations