© 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. 70018
    Prev
    Next
    INDEX
    Explanations

    compound word beginnings

    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
    huizen
    -0.73
    chaubild
    -0.71
    Estimate
    -0.70
     larvae
    -0.69
    Angel
    -0.68
    onner
    -0.67
    gos
    -0.66
     persons
    -0.65
    窝
    -0.65
    Brett
    -0.65
    POSITIVE LOGITS
     Confidence
    1.09
     confidence
    1.05
    Confidence
    0.94
     failure
    0.89
     Chern
    0.84
    فش
    0.82
    좋
    0.81
    confidence
    0.79
    usion
    0.78
    failure
    0.77
    Activations Density 0.025%

    No Known Activations