© 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. 34-GEMMASCOPE-RES-131K
    7. 60921
    Prev
    Next
    INDEX
    Explanations

    to verb constructions

    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
     possibly
    -1.13
    ַּ
    -1.08
     another
    -1.06
     wanting
    -1.04
     trebui
    -1.02
     compositeur
    -1.02
     putea
    -0.98
     Possibly
    -0.98
     vogliono
    -0.97
     selera
    -0.96
    POSITIVE LOGITS
     surprises
    1.22
     people
    1.06
    poser
    1.05
     experiment
    1.02
     joke
    1.00
     think
    0.97
     refer
    0.96
     outdoors
    0.95
     play
    0.94
     hear
    0.94
    Activations Density 0.020%

    No Known Activations