© 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. 32960
    Prev
    Next
    INDEX
    Explanations

    on the other hand

    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
    Not in Any Lists

    No Comments

    Negative Logits
     then
    -1.45
     therefore
    -1.43
     además
    -1.40
     навіть
    -1.39
     them
    -1.21
    そのため
    -1.18
     chèvre
    -1.16
     quindi
    -1.16
     inoltre
    -1.16
    でしたが
    -1.15
    POSITIVE LOGITS
    另一
    1.08
     or
    1.07
     other
    1.00
     bereits
    0.99
     '
    0.97
     may
    0.95
     if
    0.95
     could
    0.92
    querySelector
    0.91
     ('
    0.90
    Activations Density 0.036%

    No Known Activations