© 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. 84764
    Prev
    Next
    INDEX
    Explanations

    orchestra, symphony, quartet

    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
     permissions
    -0.73
     studio
    -0.72
     choir
    -0.71
    DataItem
    -0.71
    ɵɵ
    -0.71
     devs
    -0.71
     scholarship
    -0.70
     Stadtteil
    -0.70
     contemporary
    -0.70
     instructor
    -0.70
    POSITIVE LOGITS
    osphere
    0.81
    geten
    0.77
    leggen
    0.76
    straints
    0.74
    istra
    0.74
    
    0.74
     distinguer
    0.73
    换
    0.72
     exklu
    0.72
    phine
    0.72
    Activations Density 0.026%

    No Known Activations