© 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. 68921
    Prev
    Next
    INDEX
    Explanations

    start of

    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
     for
    -2.22
     должна
    -1.80
     сказала
    -1.76
     by
    -1.68
    ,
    -1.62
    ised
    -1.61
    jęt
    -1.58
     الآن
    -1.54
     from
    -1.52
    
    -1.50
    POSITIVE LOGITS
    轳
    2.19
     ''
    2.14
     antworte
    2.06
    檩
    2.05
    henswürdigkeiten
    1.95
    愎
    1.95
    梣
    1.92
    
    1.92
    寕
    1.91
     hadde
    1.89
    Activations Density 0.005%

    No Known Activations