© 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. 41710
    Prev
    Next
    INDEX
    Explanations

    section headers or labels

    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
    要在
    -1.86
    '
    -1.59
    ↵
    -1.59
     keď
    -1.48
     tendrás
    -1.45
     querr
    -1.45
     obtend
    -1.45
     cushioned
    -1.34
     révé
    -1.34
     merciless
    -1.34
    POSITIVE LOGITS
     godziny
    1.65
     mengangg
    1.63
     only
    1.63
    涠
    1.61
    と思いました
    1.57
    蹤
    1.56
     from
    1.55
    𐍉
    1.55
    かもし
    1.53
     tanya
    1.53
    Activations Density 0.003%

    No Known Activations