© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81064
    Prev
    Next
    INDEX
    Explanations

    group theory concepts

    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
    ässe
    -0.78
    ​=
    -0.78
    awtextra
    -0.76
     hipó
    -0.75
    ₗ
    -0.74
    nextDouble
    -0.73
     Kleider
    -0.73
     MEDIA
    -0.70
     Clothes
    -0.68
    ₐ
    -0.68
    POSITIVE LOGITS
     group
    2.81
    group
    2.38
     groups
    2.25
     Group
    2.17
    Group
    2.13
     گروه
    1.94
     GROUP
    1.89
     Groups
    1.86
    GROUP
    1.82
    getGroup
    1.82
    Activations Density 0.133%

    No Known Activations