© 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. 22-GEMMASCOPE-RES-131K
    4. 93090
    Prev
    Next
    INDEX
    Explanations

    want, have, or need

    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_22/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
     when
    -1.27
     RECOMMEND
    -1.15
     داریم
    -1.09
    㩒
    -1.08
     Confe
    -1.02
     داشتند
    -0.98
    
    -0.97
     イラストレーション
    -0.96
    Можно
    -0.96
    THO
    -0.93
    POSITIVE LOGITS
     want
    2.88
     muốn
    1.73
     wants
    1.66
     wanted
    1.64
     have
    1.62
    不想
    1.48
    ต้องการ
    1.46
    Want
    1.42
     chcete
    1.38
     need
    1.37
    Activations Density 0.046%

    No Known Activations