© 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. 54212
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs, modals, or 'rarely'

    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
     deportivas
    -1.02
     publicités
    -0.95
    
    -0.95
     DOING
    -0.93
    ところに
    -0.92
    ものに
    -0.91
    setzt
    -0.91
    联网
    -0.90
    não
    -0.89
    looked
    -0.89
    POSITIVE LOGITS
     does
    4.97
     do
    4.25
     did
    4.22
    Does
    3.34
     are
    3.20
     Does
    3.02
    does
    2.66
    Did
    2.53
     can
    2.41
     will
    2.39
    Activations Density 0.048%

    No Known Activations