© 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. 102626
    Prev
    Next
    INDEX
    Explanations

    authorization, scope, roles

    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
    ⇋
    -0.78
    邃
    -0.77
     virtuoso
    -0.74
    unii
    -0.72
     Orkney
    -0.69
     Utilisation
    -0.66
    jds
    -0.66
     Occupancy
    -0.65
    doa
    -0.65
    emat
    -0.64
    POSITIVE LOGITS
     authorities
    1.70
     authority
    1.61
    authorities
    1.55
    Authority
    1.47
     Authority
    1.43
     roles
    1.42
    ROLE
    1.35
    Authorities
    1.35
    authority
    1.34
     ROLE
    1.31
    Activations Density 0.002%

    No Known Activations