© 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. 89695
    Prev
    Next
    INDEX
    Explanations

    warriors and fighters

    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
     autora
    -1.07
    ophiles
    -0.91
    vidade
    -0.85
     gordo
    -0.85
     alza
    -0.85
     ló
    -0.85
     newcomers
    -0.83
     taas
    -0.83
    parade
    -0.83
    verification
    -0.82
    POSITIVE LOGITS
     warrior
    2.30
     warriors
    1.87
     fighter
    1.59
     skilled
    1.49
     Warrior
    1.44
    warrior
    1.43
     fighting
    1.34
     hunter
    1.31
     fighters
    1.30
     Warriors
    1.30
    Activations Density 0.057%

    No Known Activations