© 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. 34-GEMMASCOPE-RES-131K
    7. 48096
    Prev
    Next
    INDEX
    Explanations

    sidelined, ruled out, or retired

    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_34/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
     fp
    -0.75
     southwest
    -0.75
     reaches
    -0.75
     Киє
    -0.74
    ifrance
    -0.73
    谄
    -0.72
    둬
    -0.71
     aplicada
    -0.71
     seeming
    -0.71
     kümmern
    -0.70
    POSITIVE LOGITS
     out
    3.16
     sidelined
    2.30
     OUT
    1.69
     sidelines
    1.63
    Out
    1.51
     Out
    1.50
     sideline
    1.48
    out
    1.39
     ruled
    1.22
    OUT
    1.14
    Activations Density 0.027%

    No Known Activations