© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35208
    Prev
    Next
    INDEX
    Explanations

    predictions and forecasts

    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
     sorella
    -0.98
     is
    -0.97
    为了
    -0.96
    jn
    -0.94
    要求
    -0.94
     wymaga
    -0.94
    ıld
    -0.93
    enciales
    -0.93
    feuer
    -0.92
    рти
    -0.91
    POSITIVE LOGITS
     predictions
    2.52
     prediction
    2.42
     predicting
    2.20
     Predictions
    2.00
     predict
    1.88
     predicted
    1.85
     predicts
    1.80
    prediction
    1.80
    Predictions
    1.77
     Prediction
    1.74
    Activations Density 0.056%

    No Known Activations