© 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. 118082
    Prev
    Next
    INDEX
    Explanations

    awards for gallantry and military deeds

    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
    rification
    -0.79
     transfected
    -0.77
    ünchen
    -0.76
    gernaut
    -0.76
    obatan
    -0.75
    asiswa
    -0.74
    ЛО
    -0.74
    illos
    -0.73
    Happiness
    -0.73
    čar
    -0.73
    POSITIVE LOGITS
     bravery
    4.00
     brave
    3.86
     courage
    3.58
     courageous
    3.31
     heroic
    3.16
    brave
    2.98
     heroism
    2.94
     bravely
    2.88
     Brave
    2.77
     valor
    2.72
    Activations Density 0.059%

    No Known Activations