© 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. 6717
    Prev
    Next
    INDEX
    Explanations

    well-formatted code

    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
    gents
    1.09
     næ
    0.94
    Groups
    0.91
     reti
    0.90
     Groups
    0.90
    7
    0.90
    6
    0.90
    0
    0.89
    8
    0.88
    groups
    0.88
    POSITIVE LOGITS
    aires
    1.81
     dollar
    1.54
    aire
    1.50
    dollar
    1.44
     Dollar
    1.32
     dollars
    1.31
     dólares
    1.22
     دولار
    1.21
     rupiah
    1.20
     डॉलर
    1.20
    Activations Density 0.103%

    No Known Activations