© 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. 81642
    Prev
    Next
    INDEX
    Explanations

    evaluating performance levels

    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
    老板
    -0.81
     Patricio
    -0.76
    asta
    -0.74
     manger
    -0.73
     آسی
    -0.73
     Remake
    -0.72
    诺
    -0.68
     barista
    -0.68
    Req
    -0.66
     Grail
    -0.65
    POSITIVE LOGITS
     performers
    3.92
     performer
    3.47
     performing
    3.03
    performing
    2.47
    Performing
    2.27
     Performer
    2.23
     PERFORM
    2.22
     Performing
    2.13
    Perform
    2.03
     Perform
    1.96
    Activations Density 0.077%

    No Known Activations