© 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. 102926
    Prev
    Next
    INDEX
    Explanations

    3 functions, 3 ways, 3 classes

    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
    .
    -2.27
    ↵↵
    -2.25
    1
    -2.02
     üblichen
    -1.88
    3
    -1.88
     to
    -1.84
    2
    -1.80
    舠
    -1.78
    <i>
    -1.74
    8
    -1.73
    POSITIVE LOGITS
     kutu
    1.91
    以上です
    1.90
    笮
    1.79
    中略
    1.77
    ientos
    1.76
    おはよう
    1.75
    鐫
    1.71
     costuras
    1.67
    ።
    1.65
    顳
    1.65
    Activations Density 0.206%

    No Known Activations