© 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. 99547
    Prev
    Next
    INDEX
    Explanations

    html element ids

    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
     then
    -2.55
    This
    -2.00
    7
    -1.97
    </em>
    -1.90
     
    -1.80
    6
    -1.79
    4
    -1.70
     Here
    -1.70
     let
    -1.63
    Then
    -1.55
    POSITIVE LOGITS
     kimdir
    1.91
    ﺅ
    1.81
     maaf
    1.80
     ouvre
    1.73
     fous
    1.73
     taba
    1.71
     kutu
    1.70
     straff
    1.69
     eme
    1.68
     dolar
    1.67
    Activations Density 0.039%

    No Known Activations