© 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. 41433
    Prev
    Next
    INDEX
    Explanations

    correct or wrong choice

    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
     and
    -1.72
    6
    -1.62
     概念
    -1.48
    3
    -1.48
    那我
    -1.48
    8
    -1.46
     ATH
    -1.45
    emble
    -1.39
     häufigsten
    -1.37
    1
    -1.37
    POSITIVE LOGITS
     —
    2.16
    ↵
    1.81
     Reglamento
    1.77
    the
    1.75
     time
    1.68
     dopo
    1.67
     way
    1.63
     potente
    1.53
     depois
    1.51
     após
    1.51
    Activations Density 0.015%

    No Known Activations