© 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. 42371
    Prev
    Next
    INDEX
    Explanations

    time elapsed ago

    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
     

    -2.00
     ‘
    -1.92
     a
    -1.86
    这是一
    -1.84
    (\
    -1.78
    ’,
    -1.77
     ebenfalls
    -1.76
     практически
    -1.72
     It
    -1.71
    尤其是
    -1.71
    POSITIVE LOGITS
    骉
    1.85
     recopila
    1.77
    ずつ
    1.74
    縐
    1.72
    comme
    1.72
    捽
    1.71
     mensen
    1.70
     dingen
    1.67
    ſelves
    1.66
     whit
    1.64
    Activations Density 0.025%

    No Known Activations