© 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. 75717
    Prev
    Next
    INDEX
    Explanations

    dawn of or dawned

    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
    というわけで
    -2.20
    嘚
    -2.05
    说是
    -1.98
    ">
    -1.89
     หรือ
    -1.85
     sesiones
    -1.84
    代わり
    -1.84
     więcej
    -1.82
     lecciones
    -1.80
    優れた
    -1.78
    POSITIVE LOGITS
     of
    2.27
    );
    2.09
    şört
    1.73
    之时
    1.73
    ]
    1.72
    黎明
    1.68
    戌
    1.66
    之际
    1.65
    .
    1.60
    𔘓
    1.60
    Activations Density 0.006%

    No Known Activations