© 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. 312
    Prev
    Next
    INDEX
    Explanations

    vocational rehabilitation, professionals, training, art

    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
    -2.58
    2
    -2.50
    うわ
    -2.47
    3
    -2.41
     '
    -2.33
     ''
    -2.25
     blaue
    -2.22
     当
    -2.19
        
    -2.17
     -
    -2.14
    POSITIVE LOGITS
    汭
    2.64
    怍
    2.58
    ,’
    2.45
    
    2.41
    銠
    2.41
    嗵
    2.39
    ༀ
    2.33
    膈
    2.28
     postIndex
    2.28
     แต่
    2.28
    Activations Density 0.006%

    No Known Activations