© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60585
    Prev
    Next
    INDEX
    Explanations

    palace and related contexts

    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
    猡
    -3.30
    聍
    -2.89
    鹛
    -2.80
    拶
    -2.73
    锜
    -2.61
    していました
    -2.59
     书法
    -2.58
    泔
    -2.53
    鬭
    -2.50
    谵
    -2.48
    POSITIVE LOGITS
    ↵
    3.23
    y
    3.03
    ,’
    2.80
    ]
    2.73
    }:
    2.70
    4
    2.56
     этот
    2.41
    5
    2.38
    3
    2.38
    きれい
    2.38
    Activations Density 0.002%

    No Known Activations