© 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. 11156
    Prev
    Next
    INDEX
    Explanations

    people's names

    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
    er
    -2.95
    A
    -2.91
    でも
    -2.83
    孓
    -2.67
    焄
    -2.56
    
    -2.53
    e
    -2.53
    缡
    -2.52
    Технические
    -2.50
    すでに
    -2.48
    POSITIVE LOGITS
    咴
    3.23
    </i>
    3.05
    橚
    2.70
    逍
    2.61
     ciś
    2.36
    郿
    2.31
    ࿆
    2.28
    峩
    2.22
    ة
    2.19
     ''
    2.17
    Activations Density 0.013%

    No Known Activations