© 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. 98120
    Prev
    Next
    INDEX
    Explanations

    prediction

    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
    łecz
    -1.13
    ӏ
    -1.02
    vertre
    -0.96
    Ⅎ
    -0.96
    resten
    -0.94
    begre
    -0.93
     autorytatywna
    -0.93
     koste
    -0.90
    mannen
    -0.90
    personen
    -0.89
    POSITIVE LOGITS
     predictions
    5.78
     prediction
    5.53
     predicted
    5.13
     predict
    5.09
     predicting
    5.00
     predicts
    4.81
     Predictions
    4.69
    prediction
    4.44
     Prediction
    4.34
    Prediction
    4.34
    Activations Density 0.122%

    No Known Activations