© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 111021
    Prev
    Next
    INDEX
    Explanations

    modal verb followed by conjugated verb

    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
     rely
    -0.77
     includes
    -0.75
     says
    -0.72
     expect
    -0.72
     dizer
    -0.69
     know
    -0.69
     明
    -0.69
     notable
    -0.68
     pá
    -0.67
    漬け
    -0.67
    POSITIVE LOGITS
     được
    1.59
     wordt
    1.47
     be
    1.40
    被
    1.30
     wird
    1.25
     been
    1.22
     veniva
    1.15
    être
    1.12
    membered
    1.08
     يُ
    1.04
    Activations Density 0.106%

    No Known Activations