© 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. 34-GEMMASCOPE-RES-131K
    7. 90760
    Prev
    Next
    INDEX
    Explanations

    numeric mathematical expressions

    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_34/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
     CardView
    -0.99
     могло
    -0.94
    න්
    -0.90
     on
    -0.82
     maand
    -0.82
    middels
    -0.82
    索
    -0.79
    ню
    -0.78
    指出
    -0.78
     that
    -0.77
    POSITIVE LOGITS
     two
    1.69
     двох
    1.35
     four
    1.20
     две
    1.13
     двумя
    1.09
     three
    1.06
     “(
    1.03
    [(
    1.03
     två
    1.02
     -(
    1.00
    Activations Density 0.099%

    No Known Activations