© 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. 22-GEMMASCOPE-RES-131K
    7. 54517
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases

    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
     endi
    -1.09
     since
    -1.04
     preoc
    -1.03
     pake
    -1.02
     oks
    -1.01
     perd
    -1.00
    Since
    -1.00
     veng
    -0.96
     dollari
    -0.96
    ,
    -0.95
    POSITIVE LOGITS
     lezen
    1.28
     luglio
    1.27
     estadounidense
    1.24
    ZIONE
    1.20
     Verkäufer
    1.16
    : 
    1.15
     italie
    1.13
    magitan
    1.13
    caucasian
    1.11
    क्या
    1.09
    Activations Density 0.142%

    No Known Activations