© 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. 76156
    Prev
    Next
    INDEX
    Explanations

    electrical circuit components

    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
     δε
    -0.79
     ў
    -0.75
     verwacht
    -0.75
    視野
    -0.73
     działanie
    -0.73
    ظة
    -0.71
     يح
    -0.70
    洛克
    -0.70
    licata
    -0.69
    tetten
    -0.69
    POSITIVE LOGITS
     battery
    0.98
    ۹
    0.95
    бор
    0.82
     Groningen
    0.77
    PP
    0.75
    DC
    0.75
    DataProvider
    0.73
    ９
    0.73
     مصدر
    0.72
     Batterie
    0.72
    Activations Density 0.019%

    No Known Activations