© 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. 10339
    Prev
    Next
    INDEX
    Explanations

    preposition "to"

    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
    -
    -2.05
     to
    -2.05
     can
    -1.92
     in
    -1.70
     such
    -1.65
     is
    -1.62
     at
    -1.59
     more
    -1.59
     by
    -1.55
     like
    -1.55
    POSITIVE LOGITS
    橚
    2.38
    
    2.00
    甞
    1.91
    殛
    1.91
    鹇
    1.90
    魠
    1.86
     obce
    1.84
    깽
    1.82
    泐
    1.80
    鱚
    1.80
    Activations Density 0.024%

    No Known Activations