© 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. 93141
    Prev
    Next
    INDEX
    Explanations

    change, type, format

    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
     yaklaşık
    -0.97
    mstyle
    -0.94
    Again
    -0.92
     Again
    -0.91
    可能有
    -0.90
    AGAIN
    -0.89
    ضاف
    -0.89
    ดน
    -0.88
     regio
    -0.88
    的对象
    -0.88
    POSITIVE LOGITS
     to
    1.13
    :
    1.00
     change
    0.95
     बदल
    0.95
     changed
    0.94
     as
    0.91
     aukš
    0.91
     mī
    0.90
     preference
    0.89
     various
    0.88
    Activations Density 0.168%

    No Known Activations