© 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. 103503
    Prev
    Next
    INDEX
    Explanations

    GET / _ search

    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
     engag
    -0.79
    RequestMethod
    -0.76
     gradu
    -0.72
    IMPORTED
    -0.72
    Gruppen
    -0.71
    营
    -0.71
     sapi
    -0.70
     шу
    -0.70
    Literatur
    -0.69
     glas
    -0.69
    POSITIVE LOGITS
     kib
    1.03
    Kib
    0.97
     Kib
    0.90
    elasticsearch
    0.87
     Elasticsearch
    0.85
     elastic
    0.85
    /_
    0.84
    电影
    0.84
    kib
    0.83
     ES
    0.82
    Activations Density 0.043%

    No Known Activations