© 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. 7-GEMMASCOPE-2-RES-16K
    7. 10131
    Prev
    Next
    INDEX
    Explanations

    Japan, added, be

    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_7_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
    診療
    1.35
    RTC
    1.31
    ROOT
    1.29
    </blockquote>
    1.29
    Calibration
    1.28
    Secondly
    1.26
     thang
    1.24
    Display
    1.22
    Calculator
    1.21
    LOC
    1.20
    POSITIVE LOGITS
    া
    2.21
    دول
    2.11
    álně
    2.05
    ി
    1.95
    šit
    1.94
     الاقتصاد
    1.91
     Ekonom
    1.91
    ingos
    1.90
    igts
    1.88
    econom
    1.87
    Activations Density 0.000%

    No Known Activations