© 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. 86664
    Prev
    Next
    INDEX
    Explanations

    dielectric properties and materials

    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
    豋
    -2.44
     Now
    -2.19
    𐐪
    -2.17
     現在
    -2.11
    嫆
    -2.08
     北市
    -2.03
    你
    -2.03
     剤
    -2.03
    j
    -2.02
    ти
    -1.99
    POSITIVE LOGITS
    咵
    2.27
    "
    2.23
     elle
    2.05
    \
    1.97
    颙
    1.95
    ’
    1.94
    as
    1.88
    ൎ
    1.86
    盅
    1.85
     jednym
    1.81
    Activations Density 0.009%

    No Known Activations