© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34834
    Prev
    Next
    INDEX
    Explanations

    defining or setting variables

    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
    chenta
    -1.07
     함께
    -1.06
    cestor
    -1.05
    になってしまう
    -1.05
     then
    -1.04
     SUCH
    -1.01
     addic
    -0.99
     of
    -0.98
     grop
    -0.98
    遑
    -0.98
    POSITIVE LOGITS
    ↵↵↵
    1.15
    に
    0.99
     locul
    0.99
    ｃ
    0.98
    ↵↵↵↵
    0.94
    fielder
    0.93
    thirds
    0.93
    ⤴
    0.91
    \
    0.90
    byes
    0.90
    Activations Density 0.001%

    No Known Activations