© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30390
    Prev
    Next
    INDEX
    Explanations

    defense contractors and companies

    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
    licos
    -0.80
    Encu
    -0.78
    汽
    -0.74
    ibig
    -0.73
     explodes
    -0.73
     onstage
    -0.72
    TERA
    -0.70
    Răsp
    -0.70
    了个
    -0.69
     Achilles
    -0.69
    POSITIVE LOGITS
     defense
    1.16
     Defense
    1.06
     defence
    1.00
     Lockheed
    0.96
    defense
    0.93
    Defense
    0.92
     DEFENSE
    0.91
     Defence
    0.90
     Rhein
    0.88
     Redondo
    0.84
    Activations Density 0.026%

    No Known Activations