© 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. 64069
    Prev
    Next
    INDEX
    Explanations

    War games and combat miniatures

    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
    社會
    -0.84
    Então
    -0.78
    unidad
    -0.75
     daarvoor
    -0.73
    acheteur
    -0.71
     yardım
    -0.71
    Muito
    -0.70
    História
    -0.70
     Vr
    -0.69
    estaba
    -0.69
    POSITIVE LOGITS
    schemes
    0.83
    NOX
    0.81
     aŭ
    0.80
     Ramos
    0.79
    vidade
    0.79
    oneofs
    0.77
     Cliquez
    0.77
     impet
    0.77
    chev
    0.77
    parseInt
    0.77
    Activations Density 0.014%

    No Known Activations