© 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. 102992
    Prev
    Next
    INDEX
    Explanations

    department departments dept

    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
     sistema
    -0.76
    potranspiration
    -0.75
    知的
    -0.75
    rousel
    -0.75
     kimia
    -0.73
     quantified
    -0.72
    sister
    -0.70
     aproximadamente
    -0.69
    sistema
    -0.69
     dit
    -0.68
    POSITIVE LOGITS
     department
    1.48
     departments
    1.38
     dept
    1.28
    dept
    1.23
    Dept
    1.22
     DEPT
    1.21
     Dept
    1.17
    department
    1.17
    部门
    1.16
     Departments
    1.09
    Activations Density 0.055%

    No Known Activations