© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102840
    Prev
    Next
    INDEX
    Explanations

    adverbs 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_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
     Where
    -1.98
     Depending
    -1.95
     Assuming
    -1.95
     Ultimately
    -1.91
     Unless
    -1.89
     Furthermore
    -1.88
     According
    -1.88
     Regardless
    -1.85
     рекомендуется
    -1.84
     Because
    -1.83
    POSITIVE LOGITS
    3
    2.25
    0
    2.23
    4
    2.14
    ,/
    2.14
    8
    2.05
    ,..
    2.02
    7
    1.97
     ,.
    1.96
    ally
    1.89
    .,.
    1.85
    Activations Density 0.045%

    No Known Activations