© 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. 60978
    Prev
    Next
    INDEX
    Explanations

    negates conditions or 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
     этого
    -1.98
    Vegetarian
    -1.78
     pero
    -1.77
    茕
    -1.73
    带有
    -1.73
    裨
    -1.70
    Emo
    -1.68
    المل
    -1.67
     stolet
    -1.66
     PUSTAKA
    -1.62
    POSITIVE LOGITS
     significantly
    2.02
     geared
    2.02
     rigorously
    1.99
    ꜆
    1.98
    '
    1.90
     amazingly
    1.84
    ᠌
    1.84
     elegantly
    1.83
     predominantly
    1.82
    ㆆ
    1.81
    Activations Density 0.021%

    No Known Activations