© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72969
    Prev
    Next
    INDEX
    Explanations

    sentence beginnings describing studies

    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_10/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
     Ideally
    -1.92
    ⡯
    -1.91
     When
    -1.86
     —
    -1.84
     Ultimately
    -1.80
     Some
    -1.75
    并非
    -1.73
     Eventually
    -1.69
     enticing
    -1.69
     Shortly
    -1.67
    POSITIVE LOGITS
    粜
    2.30
    紲
    2.23
    idlertid
    2.22
    輅
    2.06
    蹰
    2.02
     contoh
    1.99
    
    1.98
    鶫
    1.94
    狳
    1.89
    𓆸
    1.89
    Activations Density 0.003%

    No Known Activations