© 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. 34-GEMMASCOPE-RES-131K
    4. 116555
    Prev
    Next
    INDEX
    Explanations

    offline usage

    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
     weed
    -0.87
     Тай
    -0.85
    Weed
    -0.80
    Portail
    -0.79
    webcam
    -0.79
     Weed
    -0.78
    ߰
    -0.76
    鲷
    -0.76
    argp
    -0.75
    ḫ
    -0.75
    POSITIVE LOGITS
     offline
    4.66
    offline
    3.81
    Offline
    3.78
     Offline
    3.66
     disconnected
    1.74
    离
    1.63
    オフ
    1.61
    线下
    1.59
     автоном
    1.57
     cache
    1.40
    Activations Density 0.059%

    No Known Activations