© 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. 10-GEMMASCOPE-RES-131K
    7. 72879
    Prev
    Next
    INDEX
    Explanations

    marvel characters and franchises

    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_10/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
    It
    -2.00
     nawet
    -1.74
     chinese
    -1.67
    There
    -1.62
     leggera
    -1.59
     ponerse
    -1.55
    5
    -1.50
     musíte
    -1.49
     french
    -1.48
     scattata
    -1.47
    POSITIVE LOGITS
     farb
    1.50
    鱨
    1.46
     to
    1.45
    檮
    1.44
    (!__
    1.42
     her
    1.40
     kurzem
    1.37
     
    1.36
     quai
    1.35
     モダン
    1.35
    Activations Density 0.003%

    No Known Activations