© 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. 10-GEMMASCOPE-RES-131K
    7. 67750
    Prev
    Next
    INDEX
    Explanations

    soldiers and military roles

    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_10/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
    好感
    -2.61
     adorable
    -2.59
     andere
    -2.56
     katk
    -2.48
     adrenaline
    -2.41
    呦
    -2.41
    </h4>
    -2.38
    Semua
    -2.33
     parfüm
    -2.33
     krä
    -2.30
    POSITIVE LOGITS
    </i>
    3.48
    does
    2.70
    籏
    2.69
    2.64
     BRARY
    2.58
    薷
    2.55
     gän
    2.53
    "},
    2.53
    いれば
    2.53
    ;
    2.50
    Activations Density 0.004%

    No Known Activations