© 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. 34-GEMMASCOPE-RES-131K
    7. 97805
    Prev
    Next
    INDEX
    Explanations

    new adapter

    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
    ListActivity
    -0.84
    sniper
    -0.71
    ListFragment
    -0.71
    體育
    -0.69
     ocasi
    -0.69
    hulk
    -0.69
     रख
    -0.69
    jav
    -0.68
     nuanced
    -0.68
     size
    -0.68
    POSITIVE LOGITS
     adapter
    1.51
    adapter
    1.48
     Adapter
    1.33
    Adapter
    1.32
    DataAdapter
    1.30
    getAdapter
    1.26
    TableAdapter
    1.20
     адап
    1.16
     ArrayAdapter
    1.10
    ListAdapter
    1.09
    Activations Density 0.006%

    No Known Activations