© 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. 103663
    Prev
    Next
    INDEX
    Explanations

    women, youth, and citizen centric services

    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
    達は
    -0.88
    コントロール
    -0.78
     controls
    -0.76
    ۜ
    -0.73
     escuchadas
    -0.73
     rekla
    -0.73
     supervise
    -0.72
    ọ
    -0.72
     opciones
    -0.70
     tejidos
    -0.70
    POSITIVE LOGITS
     empowerment
    1.44
     welfare
    1.20
     centric
    1.17
     Empowerment
    1.14
     participation
    1.13
     wing
    1.06
    Friendly
    1.02
     wings
    0.98
     friendly
    0.96
     involvement
    0.94
    Activations Density 0.025%

    No Known Activations