© 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. 71452
    Prev
    Next
    INDEX
    Explanations

    types of items and their types

    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
    љ
    -1.04
     incontr
    -1.01
    }_{
    -0.98
     gedacht
    -0.97
    
    -0.93
     かけ
    -0.90
    }")
    -0.90
     quí
    -0.89
     tamaños
    -0.89
     чет
    -0.88
    POSITIVE LOGITS
     katk
    1.09
     surgiu
    0.98
     decidiu
    0.94
     みた
    0.94
     esquecer
    0.93
     fazia
    0.92
     fået
    0.92
     opdracht
    0.91
     пирог
    0.91
    有事
    0.90
    Activations Density 0.066%

    No Known Activations