© 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. 66134
    Prev
    Next
    INDEX
    Explanations

    adverbs of manner and correctness

    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
    ньому
    -1.81
    ificantly
    -1.77
     její
    -1.64
    趼
    -1.64
     unwarranted
    -1.59
     метра
    -1.57
    ubation
    -1.55
    #*
    -1.54
    vska
    -1.54
    ów
    -1.53
    POSITIVE LOGITS
     the
    1.77
     qualcuno
    1.66
    0
    1.66
     called
    1.60
     rightly
    1.59
     ști
    1.59
     nächsten
    1.58
     pregă
    1.56
     antworte
    1.54
    ↵
    1.53
    Activations Density 0.015%

    No Known Activations