© 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. 3964
    Prev
    Next
    INDEX
    Explanations

    varied common words

    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
     sekarang
    1.29
     menu
    1.28
     체
    1.27
     pandemic
    1.26
     receiver
    1.24
     boleh
    1.23
     modular
    1.22
     fisheries
    1.20
     케
    1.20
     disease
    1.18
    POSITIVE LOGITS
     Exempl
    1.66
     Immac
    1.62
     Writers
    1.60
     Illust
    1.58
    SAA
    1.54
     Союза
    1.53
     Стар
    1.53
    Independent
    1.51
    Inspector
    1.50
    rootScope
    1.48
    Activations Density 0.061%

    No Known Activations