© 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. 111141
    Prev
    Next
    INDEX
    Explanations

    XML namespaces and categories

    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
     получить
    -0.82
     continue
    -0.82
     has
    -0.81
     talle
    -0.77
     которого
    -0.76
     laman
    -0.75
     get
    -0.75
     campeão
    -0.75
     ELECTION
    -0.75
    OOOOO
    -0.75
    POSITIVE LOGITS
    了嗎
    0.95
     čaj
    0.94
     cientos
    0.90
    Mə
    0.87
    жении
    0.82
    あらすじ
    0.82
    емого
    0.82
    Assemblée
    0.82
    demik
    0.81
    確か
    0.80
    Activations Density 0.002%

    No Known Activations