© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15234
    Prev
    Next
    INDEX
    Explanations

    shipping cost and charge

    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
     his
    -1.08
    quiler
    -1.04
     partecipanti
    -1.02
     хок
    -1.01
     aceit
    -1.00
    Ayrıca
    -0.97
     poliéster
    -0.97
     functioning
    -0.97
     ensamb
    -0.97
    
    -0.96
    POSITIVE LOGITS
     if
    1.09
     for
    1.08
    istungen
    1.06
    几种
    1.05
    ostic
    1.05
    calculated
    1.05
    ladung
    1.02
     लाग
    0.97
     chargés
    0.96
    点了点头
    0.95
    Activations Density 0.012%

    No Known Activations