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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 57597
    Prev
    Next
    INDEX
    Explanations

    lifting

    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_10/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
     But
    -2.50
    O
    -2.31
    0
    -2.27
    of
    -2.09
     tetapi
    -2.02
    v
    -1.98
    f
    -1.93
    but
    -1.88
     nhưng
    -1.85
     लेकिन
    -1.84
    POSITIVE LOGITS
     bús
    2.08
     sarcasm
    2.03
    身边的
    1.91
    它们
    1.87
     lifts
    1.84
     lidé
    1.84
     obstructions
    1.82
     ་
    1.80
    婼
    1.79
    旁邊
    1.77
    Activations Density 0.016%

    No Known Activations