© 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. 78909
    Prev
    Next
    INDEX
    Explanations

    winery tasting tours

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

    This neuron is a positional detector that responds most strongly to tokens occurring early in the document.

    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
     venit
    -0.78
    bereits
    -0.73
    MSG
    -0.73
    τία
    -0.73
     Все
    -0.73
    ULATION
    -0.71
     vocale
    -0.71
    ENSIONS
    -0.71
     urm
    -0.71
    商人
    -0.70
    POSITIVE LOGITS
     tasting
    1.42
     visitor
    1.38
     tours
    1.23
     Visitor
    1.17
     Visitors
    1.17
     visitors
    1.16
    Visitors
    1.15
     tour
    1.13
     Tasting
    1.02
    Visitor
    1.01
    Activations Density 0.020%

    No Known Activations