© 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. 98447
    Prev
    Next
    INDEX
    Explanations

    places, gene, proper names

    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
     specifik
    -1.01
     хорошего
    -0.96
     oras
    -0.95
     politika
    -0.94
     اصفه
    -0.94
    umpad
    -0.94
     deklar
    -0.93
    ???:
    -0.93
    ámica
    -0.92
    ageable
    -0.91
    POSITIVE LOGITS
    わかります
    0.96
     miejscu
    0.90
    Égypte
    0.89
    保育園
    0.87
     powiedział
    0.85
    の一つ
    0.85
    的一种
    0.85
     initializes
    0.83
     marred
    0.83
     someone
    0.82
    Activations Density 0.001%

    No Known Activations