© 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. 22-GEMMASCOPE-RES-131K
    7. 98618
    Prev
    Next
    INDEX
    Explanations

    UI elements or window settings

    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
    alucía
    -1.16
     últimos
    -1.11
     parfois
    -1.04
    नलिखित
    -1.02
    êmes
    -1.02
     désormais
    -1.01
     escritório
    -1.00
     tất
    -0.99
     that
    -0.98
    Consequently
    -0.98
    POSITIVE LOGITS
    komna
    1.04
     musées
    1.02
     развитии
    1.00
     hábit
    0.98
    สมบัติ
    0.98
     aniversario
    0.97
     hóspedes
    0.97
    嵘
    0.96
     opened
    0.96
     humilde
    0.94
    Activations Density 0.003%

    No Known Activations