© 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. 105447
    Prev
    Next
    INDEX
    Explanations

    symbols followed by punctuation

    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
     successivamente
    -1.88
    轳
    -1.74
    end
    -1.67
     addirittura
    -1.63
     subsequent
    -1.60
     persino
    -1.51
    翃
    -1.50
     defraud
    -1.50
    舁
    -1.41
    times
    -1.40
    POSITIVE LOGITS
    ’
    2.22
     itinéraires
    1.48
     emplois
    1.46
     удалить
    1.45
     investissements
    1.45
     dizaines
    1.45
     тоже
    1.43
     också
    1.40
     ersche
    1.39
     zegt
    1.39
    Activations Density 0.019%

    No Known Activations