© 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. 22-GEMMASCOPE-RES-131K
    7. 27885
    Prev
    Next
    INDEX
    Explanations

    comparison or condition

    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
    トル
    -0.82
     köz
    -0.79
     Coutinho
    -0.77
     Harcourt
    -0.75
    ;&#
    -0.75
    書房
    -0.74
    场景
    -0.74
     crossorigin
    -0.73
    pseudo
    -0.73
     YO
    -0.73
    POSITIVE LOGITS
     counterpart
    0.87
     Hälfte
    0.83
     opposite
    0.80
    іе
    0.74
     Likewise
    0.74
     αντί
    0.73
    逆に
    0.73
     equivalently
    0.72
     similarly
    0.71
     Conversely
    0.71
    Activations Density 0.086%

    No Known Activations