© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35273
    Prev
    Next
    INDEX
    Explanations

    membership or organization

    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_22/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
    jsonString
    -0.90
    HasColumn
    -0.86
    мое
    -0.84
     dicht
    -0.83
    Cantidad
    -0.82
    jeux
    -0.80
    ুল
    -0.80
    ISB
    -0.80
     Professors
    -0.80
    どちら
    -0.80
    POSITIVE LOGITS
     membership
    1.68
     memberships
    1.27
    membership
    1.26
    Membership
    1.13
     allegiance
    1.10
    维护
    1.05
     organization
    1.01
     loyalty
    0.99
     organisation
    0.98
     members
    0.97
    Activations Density 0.152%

    No Known Activations