© 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. 47949
    Prev
    Next
    INDEX
    Explanations

    for better or for worse

    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
     sooooo
    -0.84
    Christi
    -0.81
     iedereen
    -0.79
    袭
    -0.79
    Válasz
    -0.78
     nestled
    -0.77
     supremely
    -0.76
    asyarakat
    -0.75
     coupled
    -0.75
     silhouettes
    -0.74
    POSITIVE LOGITS
     rain
    1.81
     thick
    1.45
     sickness
    1.41
    through
    1.38
    Through
    1.34
     ups
    1.30
    good
    1.24
     THROUGH
    1.22
     Rain
    1.21
     whatever
    1.16
    Activations Density 0.028%

    No Known Activations