© 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. 22-GEMMASCOPE-RES-131K
    7. 28157
    Prev
    Next
    INDEX
    Explanations

    modal verbs or adverbs

    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_22/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
     wlan
    -1.06
    ഠ
    -0.98
    \%)
    -0.96
     gastron
    -0.94
     bénévol
    -0.93
     Minang
    -0.92
    |,
    -0.91
    />,
    -0.88
     criter
    -0.88
     Græ
    -0.87
    POSITIVE LOGITS
     probably
    2.42
     likely
    2.28
     surely
    2.25
     might
    2.19
     seem
    2.14
     presumably
    2.13
     may
    2.06
     apparently
    2.00
     seems
    1.98
     reportedly
    1.98
    Activations Density 0.027%

    No Known Activations