© 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. 10-GEMMASCOPE-RES-131K
    7. 127411
    Prev
    Next
    INDEX
    Explanations

    approaching or hidden threat

    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
     Aérea
    -1.99
    躥
    -1.95
     ʻ
    -1.88
    بالإنجليزية
    -1.84
     Jasa
    -1.77
     alimentare
    -1.73
     operativa
    -1.70
     immediatamente
    -1.70
    estões
    -1.70
     metropolitana
    -1.67
    POSITIVE LOGITS
    '
    2.25
     also
    2.22
     underpin
    1.86
    ೢ
    1.85
    ’
    1.80
     einer
    1.77
     weitere
    1.75
     constitución
    1.73
    ’，
    1.71
     et
    1.70
    Activations Density 0.007%

    No Known Activations