© 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. 86887
    Prev
    Next
    INDEX
    Explanations

    physical contact

    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
     attentions
    -0.87
     اطلاع
    -0.82
     själv
    -0.81
    katakan
    -0.80
    きち
    -0.79
    <0x8D>
    -0.78
    对着
    -0.77
     entraîner
    -0.77
    чих
    -0.77
    壯
    -0.76
    POSITIVE LOGITS
    に触
    1.07
     surfaces
    1.05
     areas
    1.05
     lightly
    1.03
     руками
    1.02
     inappropri
    0.96
     áreas
    0.95
     fibras
    0.94
     настройки
    0.92
     fences
    0.90
    Activations Density 0.023%

    No Known Activations