© 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. 22-GEMMASCOPE-RES-131K
    7. 128499
    Prev
    Next
    INDEX
    Explanations

    last or latter sequence

    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
     similarly
    -1.02
     Sys
    -1.01
     houd
    -0.96
     likewise
    -0.96
    类似
    -0.91
     SIMILAR
    -0.90
     イラスト
    -0.90
     optimale
    -0.89
    similar
    -0.88
    üğü
    -0.88
    POSITIVE LOGITS
     latter
    2.25
    latter
    1.66
     THAT
    1.26
    后者
    1.26
     τελευτα
    1.24
    That
    1.21
     That
    1.13
    そちら
    1.13
     those
    1.11
     đó
    1.11
    Activations Density 0.057%

    No Known Activations