© 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. 12919
    Prev
    Next
    INDEX
    Explanations

    different or each

    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
     or
    -1.11
    ⻓
    -1.10
     tradicional
    -1.09
    britanni
    -1.02
     any
    -1.00
     in
    -0.99
    kungen
    -0.99
    ItemCount
    -0.96
     full
    -0.95
    ֮
    -0.93
    POSITIVE LOGITS
     different
    3.30
    different
    2.75
     diferentes
    2.66
     différentes
    2.63
    Different
    2.61
     each
    2.52
     différents
    2.47
    不同的
    2.47
     разных
    2.44
     olika
    2.39
    Activations Density 0.205%

    No Known Activations