© 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. 70583
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    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
    <bos>
    -1.80
    warnai
    -1.72
     and
    -1.72
    lepaskan
    -1.69
    millimeters
    -1.66
     righ
    -1.63
    ">>
    -1.63
    isex
    -1.61
    espn
    -1.59
    ⭐️⭐️
    -1.59
    POSITIVE LOGITS
    We
    1.94
    ～　
    1.89
    Ekster
    1.87
    Our
    1.85
     können
    1.79
    𓐍
    1.76
    Ahol
    1.74
     possono
    1.72
    我们
    1.70
    Many
    1.66
    Activations Density 0.001%

    No Known Activations