© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 36276
    Prev
    Next
    INDEX
    Explanations

    time stamps and time difference

    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_22/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
     accogli
    -1.07
     dictates
    -1.06
     każdy
    -1.05
    毎回
    -1.02
     IConfiguration
    -1.00
     his
    -0.99
     qualsiasi
    -0.99
    听到
    -0.98
    一直
    -0.97
    ichier
    -0.96
    POSITIVE LOGITS
    AUTHORIZED
    1.05
    的实力
    1.03
    
    1.00
     Inglaterra
    0.99
    astéro
    0.98
    uttu
    0.98
     dégust
    0.98
    PONE
    0.97
     vuitton
    0.96
     hän
    0.95
    Activations Density 0.003%

    No Known Activations