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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8065
    Prev
    Next
    INDEX
    Explanations

    opponents attacking or scoring

    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
     defenses
    -0.94
     defender
    -0.86
     defense
    -0.81
     защиты
    -0.80
     Lizzie
    -0.80
     protectors
    -0.76
     ernst
    -0.76
     Arzt
    -0.76
     échelle
    -0.75
     nuoc
    -0.75
    POSITIVE LOGITS
     opponents
    1.46
     opposing
    1.38
     opponent
    1.27
     attempting
    1.11
     attackers
    1.10
     shooters
    1.04
     incoming
    1.03
     adversaries
    1.02
     hitters
    1.02
     batsman
    0.97
    Activations Density 0.010%

    No Known Activations