© 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. 13-GEMMASCOPE-2-RES-16K
    7. 13216
    Prev
    Next
    INDEX
    Explanations

    box-sizing: border-box

    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_13_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
     BANK
    1.36
     bank
    1.23
    
    1.22
     Bank
    1.19
     gid
    1.17
     ψ
    1.14
    ắc
    1.13
    ισ
    1.13
    칼
    1.12
    ᴇ
    1.11
    POSITIVE LOGITS
    Incidentally
    1.58
    which
    1.55
    Obviously
    1.54
    Apparently
    1.52
     whence
    1.44
    Which
    1.40
    Ironically
    1.36
    Interestingly
    1.34
    Fortunately
    1.34
     whereupon
    1.33
    Activations Density 0.001%

    No Known Activations