© 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. 10-GEMMASCOPE-RES-131K
    4. 19248
    Prev
    Next
    INDEX
    Explanations

    Il Divo

    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
    -2.84
     et
    -2.11
     is
    -2.00
     —
    -1.76
     Where
    -1.75
     i
    -1.73
     and
    -1.67
     de
    -1.63
    ↵
    -1.63
     to
    -1.61
    POSITIVE LOGITS
    擽
    2.42
     emblema
    1.80
    
    1.79
    IEVE
    1.75
     miliki
    1.72
     coreana
    1.68
     recipiente
    1.65
    atória
    1.63
     multiuso
    1.63
    什么呢
    1.61
    Activations Density 0.005%

    No Known Activations