© 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. 10-GEMMASCOPE-RES-131K
    7. 48061
    Prev
    Next
    INDEX
    Explanations

    fractions and mathematical expressions

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

    The neuron never fires (all activation values are zero), i.e. it doesn’t detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    Ꮴ
    -1.98
    などに
    -1.76
    泐
    -1.66
     zui
    -1.62
     этих
    -1.57
    굼
    -1.55
    コロナ禍
    -1.55
     vêtements
    -1.54
     theses
    -1.52
    なども
    -1.51
    POSITIVE LOGITS
     in
    2.42
     is
    1.80
     from
    1.65
     but
    1.51
     did
    1.50
     within
    1.48
     so
    1.48
     the
    1.48
    に行ってきました
    1.47
    IonicModule
    1.46
    Activations Density 0.010%

    No Known Activations