© 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. 73546
    Prev
    Next
    INDEX
    Explanations

    mid-century and time references

    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
    ıkları
    -0.93
     lessened
    -0.91
     side
    -0.90
     faptul
    -0.85
     câteva
    -0.85
    今まで
    -0.83
    vety
    -0.83
    言葉
    -0.82
     piensan
    -0.81
     worth
    -0.81
    POSITIVE LOGITS
     mid
    1.52
    mid
    1.17
     Mid
    1.08
     dle
    1.02
    Mid
    1.01
     of
    0.91
     contrario
    0.88
     België
    0.86
     COC
    0.86
     eerste
    0.85
    Activations Density 0.015%

    No Known Activations