© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 102500
    Prev
    Next
    INDEX
    Explanations

    containers for goods

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

    the neuron flags financial terms describing currency values and movements (e.g. depreciation, strength, dollar, Bank, “against,” “basket”).

    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
     xếp
    -0.73
    烯
    -0.71
     Kell
    -0.69
    brar
    -0.68
    Jó
    -0.68
     capacities
    -0.68
     unprotected
    -0.68
     Caucus
    -0.67
    rende
    -0.65
     licen
    -0.65
    POSITIVE LOGITS
     basket
    2.69
     baskets
    2.39
     hamper
    2.30
     hampers
    2.17
     box
    1.94
     Basket
    1.90
     boxes
    1.86
     kits
    1.82
    basket
    1.82
     bag
    1.77
    Activations Density 0.028%

    No Known Activations