© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99813
    Prev
    Next
    INDEX
    Explanations

    construct or include

    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
     được
    -1.18
     удовольствием
    -0.99
     become
    -0.97
    țele
    -0.96
     modificar
    -0.93
     blivit
    -0.92
     matematika
    -0.92
    become
    -0.91
    会被
    -0.90
    urlar
    -0.90
    POSITIVE LOGITS
     include
    2.70
     included
    2.30
     includes
    1.91
    Include
    1.84
     put
    1.71
    include
    1.71
     Include
    1.70
     includ
    1.66
     Included
    1.56
     Including
    1.55
    Activations Density 0.226%

    No Known Activations