© 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. 92239
    Prev
    Next
    INDEX
    Explanations

    Azerbaijan and breakaway regions

    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
    нень
    -0.74
    쌓
    -0.72
    στε
    -0.72
    Cfg
    -0.71
     marvel
    -0.69
    swf
    -0.69
     okreś
    -0.69
     considerate
    -0.67
    cstdlib
    -0.66
     America
    -0.65
    POSITIVE LOGITS
     Karab
    1.20
     Azer
    1.16
     Nag
    1.12
    Nag
    1.07
    Arts
    0.93
     shelling
    0.92
     conflict
    0.90
     Azerbaijan
    0.89
     Azerbai
    0.88
     shelled
    0.88
    Activations Density 0.006%

    No Known Activations