© 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. 116643
    Prev
    Next
    INDEX
    Explanations

    gathering resources and building

    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
     Carnival
    -0.72
    Carnival
    -0.69
     carnival
    -0.69
    emplacement
    -0.68
    curator
    -0.68
    quíni
    -0.67
     nemen
    -0.66
     khusus
    -0.66
    ymal
    -0.66
     disks
    -0.65
    POSITIVE LOGITS
     resource
    2.30
    resource
    1.99
     resources
    1.87
     Resource
    1.82
    Resource
    1.73
    RESOURCE
    1.64
    资源
    1.58
     ресур
    1.55
     RESOURCE
    1.54
    資源
    1.52
    Activations Density 0.023%

    No Known Activations