© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76330
    Prev
    Next
    INDEX
    Explanations

    situation awareness

    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
    ugeot
    -1.09
    鹮
    -1.08
    STERY
    -1.05
    鲽
    -1.03
    scheduled
    -1.01
    punkte
    -1.01
    INTRO
    -0.99
    趼
    -0.99
    棡
    -0.99
    aktionen
    -0.98
    POSITIVE LOGITS
     situations
    1.87
     situation
    1.77
     Situations
    1.59
     Situation
    1.47
     where
    1.43
     arises
    1.41
     arise
    1.36
     situaciones
    1.35
     circumstances
    1.33
     situación
    1.32
    Activations Density 0.021%

    No Known Activations