© 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. 84616
    Prev
    Next
    INDEX
    Explanations

    frequent places

    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
    demik
    -0.77
    紉
    -0.76
    Mü
    -0.76
     измер
    -0.75
    flight
    -0.74
    飞
    -0.73
    sibilidade
    -0.73
    代
    -0.72
    RAIN
    -0.71
    عه
    -0.71
    POSITIVE LOGITS
     frequent
    4.94
     frequ
    4.06
     frequented
    3.81
    frequent
    3.72
    frequ
    3.58
     Frequent
    3.52
    Frequent
    3.45
     fréqu
    3.42
     fréquent
    3.25
     frequency
    3.19
    Activations Density 0.077%

    No Known Activations