© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98420
    Prev
    Next
    INDEX
    Explanations

    NATO defense in the Baltics

    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
     mother
    -0.81
     university
    -0.80
     póź
    -0.79
    Man
    -0.75
     father
    -0.73
     привод
    -0.73
    Ostat
    -0.72
    fullscreen
    -0.71
     Kuchen
    -0.71
     salvare
    -0.71
    POSITIVE LOGITS
     NATO
    1.19
    Enhanced
    1.13
     rotational
    1.13
     deterrence
    1.12
     Enhanced
    1.06
     reassure
    1.05
     Assurance
    1.05
    NATO
    1.04
     Baltic
    1.03
     reassurance
    0.99
    Activations Density 0.019%

    No Known Activations