© 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. 73773
    Prev
    Next
    INDEX
    Explanations

    specifying contexts and relationships

    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
    rijf
    -1.09
     ricca
    -1.09
     exportaciones
    -1.08
     Sünden
    -1.04
     Fähigkeit
    -1.02
     treba
    -1.02
     Bewußt
    -1.01
     позволя
    -1.00
    StoryboardSegue
    -1.00
     lót
    -0.99
    POSITIVE LOGITS
     of
    2.28
     which
    1.32
    (_.
    1.04
     the
    1.04
    際には
    1.02
     different
    1.01
    "/"
    0.98
     ulike
    0.97
     diverse
    0.94
    for
    0.91
    Activations Density 0.059%

    No Known Activations