© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14051
    Prev
    Next
    INDEX
    Explanations

    math and science terminology

    np_acts-logits-general · gemini-2.5-flash-lite

    political discourse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    said
    0.53
    ann
    0.49
    ud
    0.47
    å
    0.46
    while
    0.45
     Technology
    0.45
    ag
    0.44
    á
    0.44
     Despite
    0.43
    а
    0.43
    POSITIVE LOGITS
     concat
    0.58
     codons
    0.57
     grap
    0.57
     parses
    0.56
     orbifold
    0.55
     parse
    0.55
     exif
    0.55
     dimensionality
    0.54
     instantiation
    0.54
     logarith
    0.54
    Activations Density 0.133%

    No Known Activations