© 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. 65349
    Prev
    Next
    INDEX
    Explanations

    verbs followed by complements

    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
     także
    -1.54
     árabe
    -1.51
    ughter
    -1.43
    acakt
    -1.43
    也是
    -1.42
     również
    -1.41
    ቷ
    -1.40
    ném
    -1.37
     également
    -1.34
    landı
    -1.34
    POSITIVE LOGITS
    i
    1.73
    A
    1.73
    O
    1.56
    e
    1.48
    </strong>
    1.47
    fe
    1.39
    </h4>
    1.37
     October
    1.35
    E
    1.35
     Huge
    1.34
    Activations Density 0.009%

    No Known Activations