© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43457
    Prev
    Next
    INDEX
    Explanations

    army or armies

    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
    ‪.‬‬
    -2.33
     ある
    -2.11
     \"
    -1.99
    ⩴
    -1.92
    ਾਈ
    -1.91
    ᷆
    -1.88
    本当
    -1.80
    ⡑
    -1.80
    </em>
    -1.80
    缑
    -1.77
    POSITIVE LOGITS
    )-
    2.20
     are
    2.09
    готовки
    2.02
    I
    1.96
    );
    1.89
     шанс
    1.84
    l
    1.77
     fifties
    1.76
     thirties
    1.73
     forties
    1.73
    Activations Density 0.010%

    No Known Activations