© 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. 105864
    Prev
    Next
    INDEX
    Explanations

    how [adjective/state]

    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
     of
    -2.05
     tantangan
    -2.03
     each
    -1.97
     your
    -1.92
     then
    -1.83
     it
    -1.75
    也会
    -1.66
    S
    -1.66
     lembaga
    -1.66
     throughout
    -1.65
    POSITIVE LOGITS
     emerg
    1.77
    叕
    1.75
     presid
    1.72
     ſuch
    1.66
    rolex
    1.65
    tiliz
    1.63
     учетом
    1.59
     dañ
    1.57
    gucci
    1.54
     derro
    1.52
    Activations Density 0.021%

    No Known Activations