© 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. 87018
    Prev
    Next
    INDEX
    Explanations

    actors and theatre personnel

    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
     användas
    -0.80
    velles
    -0.79
    brata
    -0.79
    τέλε
    -0.78
    TestingModule
    -0.76
    inete
    -0.76
    骚
    -0.73
    鋪
    -0.73
    참
    -0.72
     occlusion
    -0.72
    POSITIVE LOGITS
     Equity
    1.29
     Actors
    1.18
    Actors
    1.11
    Equity
    1.09
     Actor
    1.09
     equity
    1.07
     Broadway
    1.05
     theatre
    1.05
     Artistic
    1.03
     Producing
    1.02
    Activations Density 0.029%

    No Known Activations