© 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. 10317
    Prev
    Next
    INDEX
    Explanations

    similar to

    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
     ا
    1.23
     ر
    1.18
     ن
    1.16
     อ
    1.12
     ت
    1.11
     أ
    1.08
     تم
    1.08
     ك
    1.07
     ق
    1.07
     إ
    1.06
    POSITIVE LOGITS
     sollen
    1.40
    selen
    1.30
     calendário
    1.25
    억
    1.24
    
    1.22
    কান
    1.21
    unità
    1.21
    constructing
    1.18
    सूर
    1.15
    debounce
    1.14
    Activations Density 0.376%

    No Known Activations