© 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. 130860
    Prev
    Next
    INDEX
    Explanations

    politicians and Obama

    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
     principalmente
    -1.41
    ihnach
    -1.31
     heuti
    -1.25
     obtain
    -1.18
     др
    -1.17
     dlatego
    -1.16
     Ό
    -1.15
    ït
    -1.15
    begin
    -1.14
     deren
    -1.13
    POSITIVE LOGITS
     by
    1.58
    龶
    1.41
     vicina
    1.34
     内衣
    1.32
    oughby
    1.29
    鼯
    1.25
    皤
    1.25
    釭
    1.23
    szt
    1.23
     手绘
    1.20
    Activations Density 0.384%

    No Known Activations