© 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. 98348
    Prev
    Next
    INDEX
    Explanations

    Gas_ , it takes, Q: , De Ruyter

    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
    relenting
    -1.19
     its
    -1.16
    マイナス
    -1.12
     kilomètres
    -1.09
    欧式
    -1.09
     readily
    -1.09
    ˃
    -1.09
    Certainly
    -1.08
     ASSETS
    -1.07
     mètre
    -1.06
    POSITIVE LOGITS
    0
    1.29
     cost
    1.16
     fees
    1.15
     jopa
    1.12
     for
    1.12
     لكل
    1.09
     zostać
    1.07
     to
    1.06
     price
    1.05
    ค่า
    1.05
    Activations Density 0.003%

    No Known Activations