© 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. 22-GEMMASCOPE-RES-131K
    7. 39550
    Prev
    Next
    INDEX
    Explanations

    object attribute access and method calls

    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_22/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
    ieR
    -1.05
     ainda
    -0.99
    dreamstime
    -0.99
     Exists
    -0.95
     efectos
    -0.95
     Ic
    -0.93
    flask
    -0.92
    djang
    -0.92
    cinogenicity
    -0.91
    Další
    -0.90
    POSITIVE LOGITS
    there
    1.20
     būtų
    0.99
     as
    0.98
    obj
    0.93
    self
    0.90
    dot
    0.90
    ng
    0.90
    new
    0.89
     new
    0.88
     trov
    0.87
    Activations Density 0.001%

    No Known Activations