© 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. 75497
    Prev
    Next
    INDEX
    Explanations

    words starting with Med

    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
    </h3>
    -2.91
    毐
    -2.56
    剽
    -2.56
    轳
    -2.48
    鹚
    -2.44
    });
    -2.42
    先天
    -2.41
    })
    -2.39
    ^{-}\
    -2.36
    最重要
    -2.34
    POSITIVE LOGITS
    a
    3.47
    疍
    2.77
    7
    2.77
    the
    2.61
    無法
    2.59
    闢
    2.52
    6
    2.50
    狀況
    2.42
     ambientale
    2.41
     penghar
    2.38
    Activations Density 0.012%

    No Known Activations