© 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. 1169
    Prev
    Next
    INDEX
    Explanations

    atmospheric conditions and related phenomena

    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
     dicono
    -2.89
    禤
    -2.75
     réuss
    -2.70
    黢
    -2.67
     aspetta
    -2.67
    疡
    -2.66
     avevano
    -2.64
     Autó
    -2.61
     parut
    -2.58
    釹
    -2.53
    POSITIVE LOGITS
    .
    3.83
    ↵
    2.78
    '
    2.61
    ↵↵
    2.41
     sogen
    2.30
     ehemal
    2.14
     To
    2.09
     sowohl
    2.08
    {
    2.06
     strive
    2.05
    Activations Density 0.019%

    No Known Activations