© 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. 53999
    Prev
    Next
    INDEX
    Explanations

    quantity or contents

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

    The neuron fires strongly on multiword expressions that denote large quantities or loads using container nouns (e.g. “truck load,” “barrels of,” “bag of”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Familienname
    -0.79
     prestaciones
    -0.73
    üğü
    -0.73
    髋
    -0.73
     ユーザー
    -0.73
     Kig
    -0.72
    Exceptional
    -0.71
    veloppement
    -0.69
    辅
    -0.69
    oding
    -0.68
    POSITIVE LOGITS
    ful
    3.23
    fuls
    2.48
     full
    2.48
    load
    2.36
    full
    2.33
     load
    2.16
    FUL
    2.14
    loads
    1.83
    eload
    1.80
     loads
    1.74
    Activations Density 0.048%

    No Known Activations