© 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. 83679
    Prev
    Next
    INDEX
    Explanations

    Classifier fit, accuracy, metrics

    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
     blí
    -0.98
     BytesLike
    -0.79
     engraçadas
    -0.79
     治療
    -0.78
    vskip
    -0.78
    ajaan
    -0.77
     yrity
    -0.77
    asaan
    -0.76
     condena
    -0.75
     Keras
    -0.75
    POSITIVE LOGITS
    NESS
    0.92
     accuracy
    0.83
    iten
    0.81
    ёв
    0.77
    accuracy
    0.77
     Ness
    0.77
     Grimal
    0.73
    Metrics
    0.72
     מד
    0.70
     SCALE
    0.70
    Activations Density 0.009%

    No Known Activations