© 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. 54039
    Prev
    Next
    INDEX
    Explanations

    bench and following words

    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
    ernan
    -0.96
     erwähnten
    -0.92
     houſe
    -0.90
     находятся
    -0.87
    glieder
    -0.84
     уди
    -0.84
     Continuing
    -0.82
    異なります
    -0.81
     elegantly
    -0.81
    感觉到
    -0.79
    POSITIVE LOGITS
    bench
    1.66
     bench
    1.49
    Bench
    1.48
     Bench
    1.38
    BENCH
    1.15
     BEN
    0.96
    marks
    0.95
    હે
    0.92
    égias
    0.89
    prot
    0.88
    Activations Density 0.006%

    No Known Activations