© 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. 93647
    Prev
    Next
    INDEX
    Explanations

    Half-Life, patents, names

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron primarily detects the title “Half-Life 2,” especially when it appears as “Half-Life 2 is a science fiction first-person shooter…”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     drinkers
    -0.78
     सम
    -0.75
    kaper
    -0.74
    認
    -0.73
     "?"
    -0.73
     fouling
    -0.71
     drinker
    -0.71
    ïd
    -0.71
     hipó
    -0.69
    上で
    -0.69
    POSITIVE LOGITS
     Aly
    1.42
    Aly
    1.20
     Combine
    1.15
     Xen
    1.08
    Combine
    1.04
     Freeman
    0.97
     lambda
    0.96
     aly
    0.96
     HL
    0.95
     Barney
    0.95
    Activations Density 0.032%

    No Known Activations