© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25124
    Prev
    Next
    INDEX
    Explanations

    said

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Recently
    -1.45
     Recently
    -1.25
     recently
    -1.23
     recientemente
    -1.20
     recent
    -1.02
     visitó
    -1.00
     digelar
    -0.99
     formó
    -0.96
     July
    -0.95
    砂糖
    -0.95
    POSITIVE LOGITS
    ","\
    1.23
     was
    1.14
     afterwards
    1.10
     Questa
    1.10
     afterward
    1.09
     tonight
    1.08
     était
    1.05
     lehe
    1.05
     after
    1.03
    泵
    1.02
    Activations Density 0.012%

    No Known Activations