© 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. 33463
    Prev
    Next
    INDEX
    Explanations

    persisting until today

    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
     wcześniej
    -1.29
     previous
    -1.13
     previously
    -1.11
     agujas
    -1.07
     habia
    -1.04
     ранее
    -1.02
     πριν
    -1.02
     eerder
    -1.02
     gömlek
    -1.01
     mittelalter
    -1.01
    POSITIVE LOGITS
     today
    3.83
     to
    3.34
    至今
    3.27
    today
    3.06
     aujourd
    2.94
    今でも
    2.84
     till
    2.84
     still
    2.77
     आज
    2.75
     heute
    2.72
    Activations Density 0.058%

    No Known Activations