© 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. 82556
    Prev
    Next
    INDEX
    Explanations

    items and goods

    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
    unächst
    -0.80
     Geraadpleegd
    -0.80
    Oni
    -0.80
    特征
    -0.80
    intptr
    -0.79
     تصریح
    -0.78
    Lato
    -0.77
    ⫘
    -0.75
    ,
    -0.75
     Buying
    -0.75
    POSITIVE LOGITS
     items
    5.00
     item
    3.63
    items
    3.33
    Items
    3.06
     Items
    3.02
     ITEMS
    2.66
    ITEMS
    2.45
    item
    2.44
    アイテム
    2.44
     things
    2.25
    Activations Density 0.091%

    No Known Activations