© 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. 20493
    Prev
    Next
    INDEX
    Explanations

    made of [material]

    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
    because
    -2.22
    >-->
    -1.91
    𓋼
    -1.84
     带
    -1.82
    鹛
    -1.81
     locul
    -1.79
    赑
    -1.73
    ſſen
    -1.69
    NetworkInfo
    -1.68
     awakeFromNib
    -1.68
    POSITIVE LOGITS
     افرادی
    1.99
    갇
    1.81
     Natürlich
    1.81
     какого
    1.77
    、“
    1.74
    頭皮
    1.67
     wahre
    1.66
     vasto
    1.66
     enamor
    1.66
     également
    1.66
    Activations Density 0.011%

    No Known Activations