© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31205
    Prev
    Next
    INDEX
    Explanations

    experts

    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
     персонал
    -0.93
    neous
    -0.84
    tya
    -0.83
    Trader
    -0.82
    tivities
    -0.81
    beams
    -0.80
     kilómetros
    -0.80
    Builders
    -0.79
    Photographer
    -0.79
    :['
    -0.78
    POSITIVE LOGITS
     experts
    6.06
     expert
    5.19
    experts
    4.34
    expert
    4.06
     Experts
    4.06
    Experts
    4.03
     экспер
    3.91
     specialists
    3.77
     expertos
    3.73
    专家
    3.72
    Activations Density 0.108%

    No Known Activations