© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67819
    Prev
    Next
    INDEX
    Explanations

    all-time superlatives

    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
    蘼
    -2.16
    但也
    -2.00
    umerable
    -1.98
     indicando
    -1.97
    屃
    -1.92
    觊
    -1.91
     entrando
    -1.84
    ܔ
    -1.82
     promin
    -1.80
     ★★★★
    -1.80
    POSITIVE LOGITS
    ࿚
    2.25
    li
    2.11
     verwan
    1.98
     bekämp
    1.98
     stehe
    1.96
    l
    1.95
    浤
    1.95
     wüns
    1.90
    Also
    1.89
     befür
    1.89
    Activations Density 0.001%

    No Known Activations