Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7943
    Prev
    Next
    INDEX
    Explanations

    wars, fights, and battles

    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
    JOY
    -0.96
    Viitteet
    -0.88
    점
    -0.81
    medlem
    -0.79
    rojo
    -0.78
    Ladder
    -0.76
     femeninos
    -0.76
    stereotype
    -0.76
     Kartu
    -0.75
     Шаг
    -0.75
    POSITIVE LOGITS
     battle
    4.59
     battles
    3.80
     fight
    3.72
    battle
    3.33
     struggle
    3.06
    Battle
    2.78
     Battle
    2.77
     fights
    2.66
    fight
    2.64
     battled
    2.48
    Activations Density 0.126%

    No Known Activations