© 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. 48212
    Prev
    Next
    INDEX
    Explanations

    solar collector

    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
    öng
    -0.75
     ivory
    -0.72
    電源
    -0.71
    𝐠
    -0.71
     nitrogen
    -0.71
     純正
    -0.69
     nė
    -0.69
     ложка
    -0.68
    DISP
    -0.68
     keterangan
    -0.68
    POSITIVE LOGITS
     collector
    2.06
     solar
    2.02
    collector
    1.82
     Collector
    1.77
     collectors
    1.76
     Solar
    1.67
    solar
    1.66
    Solar
    1.59
    Collector
    1.48
     Collectors
    1.42
    Activations Density 0.018%

    No Known Activations