© 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. 76397
    Prev
    Next
    INDEX
    Explanations

    airport gates

    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
     Institu
    -0.83
    tps
    -0.81
    FFIC
    -0.79
     бал
    -0.79
     Umfeld
    -0.77
    ղ
    -0.74
    ൂ
    -0.73
     surgeon
    -0.73
     quartos
    -0.72
    じる
    -0.72
    POSITIVE LOGITS
     gate
    2.52
     gates
    2.11
     Gate
    2.05
    Gate
    1.94
    gate
    1.73
    Gates
    1.69
     Gates
    1.63
    gates
    1.48
    GATE
    1.38
     GATE
    1.38
    Activations Density 0.027%

    No Known Activations