© 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. 931
    Prev
    Next
    INDEX
    Explanations

    per cent

    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
    嵎
    -1.93
     sowohl
    -1.81
     apaixon
    -1.76
     sécher
    -1.76
    尨
    -1.72
    摇了
    -1.66
    Ꭸ
    -1.63
    !”
    -1.61
     проєкту
    -1.58
    豋
    -1.58
    POSITIVE LOGITS
    ,
    1.77
     These
    1.48
     如果
    1.46
    =
    1.46
     wodurch
    1.45
    lblNewLabel
    1.44
     dicendo
    1.42
     Their
    1.42
     It
    1.41
    ędzynarod
    1.40
    Activations Density 0.005%

    No Known Activations