© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43428
    Prev
    Next
    INDEX
    Explanations

    lethal danger and death

    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_10/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
    垍
    -1.61
    «.
    -1.53
     點
    -1.52
     ‹
    -1.52
     ʻ
    -1.50
    女
    -1.48
    Beschrijving
    -1.44
     豚
    -1.43
    …»
    -1.41
     devotee
    -1.41
    POSITIVE LOGITS
     you
    1.77
    .
    1.55
    也
    1.48
     It
    1.41
     death
    1.32
     Bescheid
    1.30
    ถาม
    1.29
     Death
    1.28
     их
    1.28
    はもちろん
    1.27
    Activations Density 0.052%

    No Known Activations