© 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. 34-GEMMASCOPE-RES-131K
    7. 48234
    Prev
    Next
    INDEX
    Explanations

    adverbs ending in -ly

    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_34/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
     personally
    -1.13
     extensively
    -1.07
     perfectly
    -1.03
     faisait
    -0.98
    nofollow
    -0.97
     broadly
    -0.96
     sorely
    -0.96
     wrongfully
    -0.95
    cnpj
    -0.95
     of
    -0.94
    POSITIVE LOGITS
    yyy
    1.10
    yyyyy
    1.09
    yyyy
    1.05
    ishly
    0.97
    lllllllll
    0.94
    trucks
    0.93
     demais
    0.93
    BeforeClass
    0.90
     parlant
    0.88
     enough
    0.86
    Activations Density 0.125%

    No Known Activations