© 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. 119966
    Prev
    Next
    INDEX
    Explanations

    Mark Twain, Victoria's Secret Angels

    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
    הם
    -1.51
     and
    -1.49
     możemy
    -1.47
    ších
    -1.45
     wich
    -1.43
    짬
    -1.41
     zapato
    -1.41
     можем
    -1.39
    ﹂
    -1.38
    ଵ
    -1.35
    POSITIVE LOGITS
     to
    2.16
    end
    1.77
     dopo
    1.65
     they
    1.63
    裢
    1.62
     It
    1.57
     The
    1.57
    ologic
    1.52
    lo
    1.51
     THERE
    1.49
    Activations Density 0.177%

    No Known Activations