© 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. 22-GEMMASCOPE-RES-131K
    7. 9658
    Prev
    Next
    INDEX
    Explanations

    gradually increasing over time

    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
     hvil
    -1.11
     harap
    -1.05
    Diagnos
    -1.01
     both
    -1.01
     flott
    -0.99
    〒
    -0.93
    確かに
    -0.93
     kristal
    -0.92
     raisons
    -0.92
    Profess
    -0.91
    POSITIVE LOGITS
     gradually
    2.38
     dần
    1.83
     постепенно
    1.77
     gradual
    1.73
     then
    1.66
     slowly
    1.65
     until
    1.61
     Gradually
    1.60
     week
    1.55
     eventually
    1.49
    Activations Density 0.016%

    No Known Activations