© 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. 103731
    Prev
    Next
    INDEX
    Explanations

    Estonian, Latvian, or foreign place names

    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
     ſo
    -0.87
    👶
    -0.80
    >]
    -0.77
    anyaan
    -0.75
     波
    -0.75
     solare
    -0.75
    faring
    -0.73
    🌊
    -0.73
    calça
    -0.73
    βα
    -0.73
    POSITIVE LOGITS
     inexpensive
    0.78
     teach
    0.72
     właści
    0.69
     Wait
    0.68
     liefert
    0.68
     espera
    0.68
     standardized
    0.67
    patched
    0.66
     proprietary
    0.66
     unintelligible
    0.66
    Activations Density 0.019%

    No Known Activations