© 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. 6848
    Prev
    Next
    INDEX
    Explanations

    domain names ending in com or org

    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
    ことも
    -1.15
    事が
    -1.07
     of
    -1.02
     Moreover
    -1.01
     inoltre
    -0.98
     Count
    -0.97
     sfondo
    -0.95
    感じで
    -0.94
    men
    -0.91
    に使用
    -0.91
    POSITIVE LOGITS
    lify
    1.07
    waktu
    1.05
     website
    1.04
    ってみました
    1.01
    /?
    1.00
    pilih
    0.99
    reservations
    0.99
     Warhol
    0.98
     formulaire
    0.97
    /.../
    0.97
    Activations Density 0.060%

    No Known Activations