© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58415
    Prev
    Next
    INDEX
    Explanations

    various services

    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_34/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
    galeria
    -0.86
    cabeza
    -0.83
     tributaries
    -0.81
    cámara
    -0.81
    muñeca
    -0.79
    Én
    -0.78
    Carrot
    -0.78
    Yann
    -0.78
    código
    -0.76
     مجموعة
    -0.76
    POSITIVE LOGITS
     service
    2.44
     services
    2.42
    サービス
    1.79
    服务
    1.76
    service
    1.67
    Service
    1.66
     servicio
    1.64
     Services
    1.55
     Service
    1.53
    服務
    1.53
    Activations Density 0.041%

    No Known Activations