© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43094
    Prev
    Next
    INDEX
    Explanations

    Lisnadill place name

    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
    וּ
    -1.48
    yeur
    -1.34
    brokes
    -1.30
    annica
    -1.27
     člá
    -1.26
    jącego
    -1.24
     бампер
    -1.23
    iyaki
    -1.23
     in
    -1.23
    ेमाल
    -1.22
    POSITIVE LOGITS
     such
    1.56
    νονται
    1.40
     all
    1.38
     how
    1.33
     either
    1.30
    用
    1.27
    各
    1.27
     everything
    1.19
    在我们
    1.19
    都
    1.15
    Activations Density 0.013%

    No Known Activations