© 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. 10-GEMMASCOPE-RES-131K
    7. 85581
    Prev
    Next
    INDEX
    Explanations

    first and last

    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
     männis
    -1.47
     caminhão
    -1.22
     instituto
    -1.20
     tempes
    -1.20
    Its
    -1.20
    Diction
    -1.19
    異なります
    -1.19
     deles
    -1.17
    ęku
    -1.16
     kanilang
    -1.16
    POSITIVE LOGITS
     who
    1.67
     your
    1.66
    :{
    1.38
    ）」
    1.32
     have
    1.31
     up
    1.22
     into
    1.22
    色列
    1.13
     from
    1.13
     kağıdı
    1.13
    Activations Density 0.168%

    No Known Activations