© 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. 84200
    Prev
    Next
    INDEX
    Explanations

    content added or updated frequently

    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
    wald
    -0.93
     both
    -0.83
    gathered
    -0.82
    icken
    -0.80
     combined
    -0.79
    OfClass
    -0.79
     peito
    -0.79
     but
    -0.77
     largest
    -0.77
    zade
    -0.76
    POSITIVE LOGITS
     updates
    1.43
     updated
    1.38
     new
    1.30
     uploaded
    1.30
     refreshed
    1.27
     update
    1.26
    更新
    1.18
     posted
    1.13
    ẩn
    1.05
     published
    1.02
    Activations Density 0.096%

    No Known Activations