© 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. 116558
    Prev
    Next
    INDEX
    Explanations

    rotary tools and instruments

    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
    iería
    -0.87
    Rental
    -0.84
    BUCKET
    -0.82
     السياس
    -0.79
     Rental
    -0.78
     čás
    -0.78
    Rise
    -0.78
     Rise
    -0.77
     Bucket
    -0.77
     lobes
    -0.75
    POSITIVE LOGITS
     hobby
    0.98
     dental
    0.94
     jew
    0.84
     miniature
    0.84
     micro
    0.84
    hobby
    0.82
     jewellery
    0.82
     microscope
    0.82
     art
    0.81
     jewelry
    0.80
    Activations Density 0.018%

    No Known Activations