© 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. 98905
    Prev
    Next
    INDEX
    Explanations

    offense and defense

    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
    urator
    -0.82
     especí
    -0.82
    sible
    -0.81
     société
    -0.79
     prends
    -0.76
    ец
    -0.75
    anager
    -0.75
    APIC
    -0.75
     tonos
    -0.75
    menü
    -0.75
    POSITIVE LOGITS
     offense
    2.81
     defense
    2.80
     defence
    2.17
    defense
    2.06
     offence
    1.83
    Defense
    1.83
     Defense
    1.61
     defenses
    1.55
     DEFENSE
    1.55
     Offense
    1.48
    Activations Density 0.032%

    No Known Activations