© 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. 69899
    Prev
    Next
    INDEX
    Explanations

    outliers and anomalies

    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
     Callum
    -0.89
    ticias
    -0.84
     સ્
    -0.82
     couteau
    -0.82
     descomp
    -0.81
    itados
    -0.79
    龠
    -0.78
    侧面
    -0.78
    tible
    -0.77
     criticizing
    -0.77
    POSITIVE LOGITS
     outliers
    4.81
     outlier
    4.66
     outlying
    2.75
     anomaly
    2.55
     Out
    2.45
     anomalous
    2.38
    Out
    2.25
     anomalies
    2.23
     abnormal
    2.08
    异常
    2.06
    Activations Density 0.058%

    No Known Activations