© 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. 42061
    Prev
    Next
    INDEX
    Explanations

    handling events and data

    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
    "
    -1.81
    璈
    -1.79
    啕
    -1.63
    aphne
    -1.60
    峭
    -1.59
    趼
    -1.56
    起码
    -1.52
     DIDN
    -1.52
    変わらない
    -1.52
     dél
    -1.51
    POSITIVE LOGITS
    就
    1.96
    蘼
    1.95
     }
    1.95
     =
    1.94
    </em>
    1.85
    ie
    1.81
    或
    1.79
    ");
    1.77
    处理
    1.76
     sicheren
    1.71
    Activations Density 0.017%

    No Known Activations