© 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. 22-GEMMASCOPE-2-RES-16K
    7. 6645
    Prev
    Next
    INDEX
    Explanations

    set each

    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_22_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
    e
    1.06
     Twitter
    1.04
     socially
    1.03
    ea
    1.01
    ام
    1.00
     Prince
    1.00
     Umbrella
    1.00
     sociological
    0.99
     Austen
    0.99
    eV
    0.99
    POSITIVE LOGITS
     nødv
    1.22
    際は
    1.12
    際には
    1.06
    bedingt
    1.02
    時は
    1.02
    =*
    1.00
     svých
    0.99
     zaś
    0.98
    方は
    0.98
     dihap
    0.98
    Activations Density 0.000%

    No Known Activations