© 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. 34473
    Prev
    Next
    INDEX
    Explanations

    package.json or code

    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
    Unit
    -0.77
     jaką
    -0.77
    Brook
    -0.77
    robot
    -0.75
    ukone
    -0.73
    أ
    -0.72
     aceea
    -0.72
    Deal
    -0.70
    سبب
    -0.69
    SPRING
    -0.69
    POSITIVE LOGITS
     registry
    0.89
    REFERENCE
    0.83
    ItemModel
    0.76
    Debugging
    0.74
     Mod
    0.74
    registry
    0.73
    尕
    0.73
     Regist
    0.71
    говари
    0.71
     creative
    0.71
    Activations Density 0.012%

    No Known Activations