© 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. 69949
    Prev
    Next
    INDEX
    Explanations

    battle and war terms

    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
    aryl
    -0.89
    kovou
    -0.88
    cích
    -0.85
     jär
    -0.83
    јани
    -0.82
    ägen
    -0.82
    ConstraintSet
    -0.81
    原型
    -0.80
     vů
    -0.79
     ransomware
    -0.79
    POSITIVE LOGITS
     battle
    3.59
     battlefield
    3.55
     war
    3.52
    battle
    2.94
     battles
    2.92
     wars
    2.84
     warfare
    2.84
    Battle
    2.38
     savaş
    2.34
     Battle
    2.31
    Activations Density 0.065%

    No Known Activations