© 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. 118422
    Prev
    Next
    INDEX
    Explanations

    capture any

    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
    
    -1.30
     Some
    -1.27
    :
    -1.12
     कुछ
    -1.09
     we
    -1.08
    níků
    -1.06
    queryInterface
    -1.06
     first
    -1.05
    有一些
    -1.05
    ⎠
    -1.02
    POSITIVE LOGITS
     any
    2.39
     dowol
    2.03
     ANY
    1.89
    任意
    1.80
     anywhere
    1.80
     anyone
    1.79
     thousands
    1.78
     qualsiasi
    1.77
     anything
    1.73
     cualquier
    1.73
    Activations Density 0.177%

    No Known Activations