© 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. 2966
    Prev
    Next
    INDEX
    Explanations

    military academies and colleges

    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
    总经理
    -0.73
    textAlign
    -0.73
     التع
    -0.72
    Marvel
    -0.71
    nyv
    -0.71
    nasio
    -0.71
    民国
    -0.70
    SYNOPSIS
    -0.69
     Fähigkeit
    -0.68
     Cym
    -0.67
    POSITIVE LOGITS
     Academy
    1.66
     academy
    1.57
     Naval
    1.55
     academies
    1.38
     cadets
    1.37
     cadet
    1.29
    academy
    1.25
     Merchant
    1.24
     ACADEMY
    1.23
    Naval
    1.20
    Activations Density 0.030%

    No Known Activations