© 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. 41596
    Prev
    Next
    INDEX
    Explanations

    HTML alignment attributes

    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
    ’
    -2.78
    ^{
    -2.63
     Until
    -2.47
    姈
    -2.47
     принято
    -2.45
    </strong>
    -2.38
     Evidently
    -2.28
     They
    -2.28
    ized
    -2.25
    енты
    -2.22
    POSITIVE LOGITS
    馓
    2.89
     helst
    2.48
    két
    2.34
    餵
    2.34
     poupée
    2.34
    是個
    2.34
     trasero
    2.31
    澌
    2.23
     méxico
    2.20
     brukt
    2.20
    Activations Density 0.004%

    No Known Activations