© 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. 84569
    Prev
    Next
    INDEX
    Explanations

    administrative and municipal district

    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
    રે
    -0.85
    Sympto
    -0.82
     sky
    -0.79
     fresher
    -0.75
     Cheer
    -0.73
    prior
    -0.72
    responsive
    -0.71
    оне
    -0.68
    fresh
    -0.68
     Pemberton
    -0.68
    POSITIVE LOGITS
     digitale
    0.95
     digitalen
    0.89
    taje
    0.75
    Trajectory
    0.72
     digital
    0.70
     traditionelle
    0.68
    xaml
    0.68
    ज्ञान
    0.68
    setCellValue
    0.66
     digitales
    0.66
    Activations Density 0.086%

    No Known Activations