© 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. 3918
    Prev
    Next
    INDEX
    Explanations

    data processing and selection

    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
    Cam
    1.39
    ặn
    1.39
    Ca
    1.37
    Vi
    1.33
     you
    1.30
    ус
    1.29
     gắng
    1.28
    sam
    1.26
     pre
    1.26
    B
    1.26
    POSITIVE LOGITS
     ऑफ
    2.31
     nodal
    2.06
     των
    2.04
    indrome
    2.02
     ofthe
    2.02
     biodivers
    1.98
    QUENCY
    1.97
    ofthe
    1.94
     της
    1.90
     عالمی
    1.87
    Activations Density 0.065%

    No Known Activations