© 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. 32880
    Prev
    Next
    INDEX
    Explanations

    deterrence and strategic calculations

    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
    Betsy
    -0.84
     铜
    -0.83
    mickey
    -0.77
    agora
    -0.76
    Medidas
    -0.75
     Gom
    -0.75
    ônio
    -0.74
    JMenuItem
    -0.73
     cleaned
    -0.72
    Distances
    -0.72
    POSITIVE LOGITS
     declaratory
    1.02
     deterred
    0.93
    ízo
    0.91
     deter
    0.88
     calculations
    0.82
    Deter
    0.81
     deterrence
    0.81
     restraining
    0.81
     Deter
    0.80
    Rollback
    0.80
    Activations Density 0.021%

    No Known Activations