© 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. 22-GEMMASCOPE-RES-131K
    4. 36246
    Prev
    Next
    INDEX
    Explanations

    numbers and counts following items

    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_22/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
     fing
    -0.90
     w
    -0.86
    見ると
    -0.85
     ווא
    -0.82
     origins
    -0.80
    問合せ
    -0.78
    ילות
    -0.78
     einerseits
    -0.77
     tomando
    -0.77
    投诉
    -0.76
    POSITIVE LOGITS
     revelado
    1.05
     fiables
    1.05
     luxus
    1.01
     affichés
    1.00
     univerz
    1.00
    ización
    0.97
    אָ
    0.96
     boire
    0.95
     Unies
    0.94
     tragé
    0.92
    Activations Density 0.142%

    No Known Activations