© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43811
    Prev
    Next
    INDEX
    Explanations

    to verbs of opportunity

    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
     its
    -2.00
     attiv
    -1.80
    }$
    -1.79
     mengganggu
    -1.72
     sicht
    -1.63
     which
    -1.62
    甶
    -1.59
     they
    -1.57
     celebrated
    -1.57
     burbu
    -1.56
    POSITIVE LOGITS
     THEY
    1.89
    趼
    1.70
     stř
    1.70
    清理
    1.63
    e
    1.62
     играет
    1.60
     четыре
    1.59
    Economía
    1.57
    üğü
    1.56
     який
    1.55
    Activations Density 0.010%

    No Known Activations