© 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. 130582
    Prev
    Next
    INDEX
    Explanations

    missed opportunities and events

    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
     When
    -2.39
    >
    -2.16
     recientes
    -2.05
     neuesten
    -2.02
     剤
    -1.98
     new
    -1.95
     newest
    -1.95
    悧
    -1.84
     製品
    -1.83
    \
    -1.82
    POSITIVE LOGITS
    𞤢
    2.44
    ↵
    2.30
     tinham
    2.20
    縯
    2.14
    ୩
    2.11
    ︐
    2.06
    dengan
    2.00
    ⟝
    1.99
    鐿
    1.99
     économies
    1.98
    Activations Density 0.010%

    No Known Activations