© 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. 76450
    Prev
    Next
    INDEX
    Explanations

    Tuesday, Regional, Internal, Mantra

    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
    മ്പ
    -0.91
    セット
    -0.83
    ))+
    -0.78
     parking
    -0.78
     Microscopy
    -0.77
     kebakaran
    -0.75
     покрытия
    -0.71
    ượt
    -0.71
    yti
    -0.70
     Parking
    -0.70
    POSITIVE LOGITS
     Trigger
    0.76
     triggering
    0.75
    olanda
    0.73
     whitespace
    0.72
    Absent
    0.71
    EUROPEAN
    0.71
     estadounidenses
    0.70
    재
    0.70
     ナチュラル
    0.70
     transforma
    0.69
    Activations Density 0.006%

    No Known Activations