© 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. 41956
    Prev
    Next
    INDEX
    Explanations

    electrostatic discharge (ESD)

    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
    犼
    -3.16
    geſ
    -3.11
    ⸰
    -2.95
    缑
    -2.91
    𞤢
    -2.89
    🫅
    -2.89
    戋
    -2.88
    ⸫
    -2.88
    盉
    -2.73
    ܖ
    -2.69
    POSITIVE LOGITS
     &
    2.89
     While
    2.89
     Currently
    2.80
    e
    2.70
     Now
    2.59
    ↵
    2.52
     Particularly
    2.48
     Surprisingly
    2.47
     Quite
    2.41
    i
    2.41
    Activations Density 0.036%

    No Known Activations