© 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. 14899
    Prev
    Next
    INDEX
    Explanations

    last of something

    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
     and
    -1.94
     both
    -1.70
     already
    -1.55
    Both
    -1.45
    órica
    -1.44
     viviendas
    -1.39
    iteiten
    -1.39
     Both
    -1.39
    usitis
    -1.36
    zló
    -1.34
    POSITIVE LOGITS
     last
    1.42
     чтоб
    1.39
    last
    1.37
     другие
    1.32
    𓍊
    1.31
    ={};
    1.26
     этих
    1.24
     letzte
    1.24
     that
    1.23
    
    1.23
    Activations Density 0.082%

    No Known Activations