© 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. 106869
    Prev
    Next
    INDEX
    Explanations

    militia, volunteers, or armed forces

    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
    nictví
    -0.99
     HUD
    -0.94
    celle
    -0.85
    ᐢ
    -0.82
     berle
    -0.82
    katkan
    -0.81
    IFICATE
    -0.80
    Witam
    -0.80
    Pä
    -0.78
     Seorang
    -0.77
    POSITIVE LOGITS
     militia
    2.19
     volunteer
    2.14
     Volunteer
    1.74
     volunteers
    1.66
    Volunteer
    1.63
     mili
    1.63
     armed
    1.50
     Militia
    1.43
    mili
    1.40
    volunteer
    1.40
    Activations Density 0.039%

    No Known Activations