© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60838
    Prev
    Next
    INDEX
    Explanations

    alien, UFO, extraterrestrial

    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
     leop
    -0.90
    ཚ
    -0.79
    AttributedString
    -0.77
     Tigers
    -0.75
     vulture
    -0.74
     tigers
    -0.74
    ARROW
    -0.74
     ль
    -0.73
    Arrow
    -0.73
     apprentices
    -0.72
    POSITIVE LOGITS
     alien
    3.66
     aliens
    3.59
     Alien
    2.94
    Alien
    2.84
    alien
    2.84
     Aliens
    2.66
    aliens
    2.50
     UFO
    2.48
     extrater
    2.44
    👽
    2.34
    Activations Density 0.045%

    No Known Activations