© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 92305
    Prev
    Next
    INDEX
    Explanations

    scenic routes and trails

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

    This neuron fires on mentions of named roadways and trails (e.g. “Scenic Byway,” “Trail,” etc.).

    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
    freezing
    -0.89
     freezing
    -0.82
     beach
    -0.82
     nightclub
    -0.81
     bỏng
    -0.79
    ಏ
    -0.79
    beach
    -0.78
    ၀
    -0.77
     אַ
    -0.77
    čenie
    -0.77
    POSITIVE LOGITS
     touring
    1.35
    Route
    1.29
     Touring
    1.27
     Route
    1.24
    route
    1.23
     tour
    1.20
     itinerary
    1.16
     route
    1.16
     routes
    1.16
    Tour
    1.11
    Activations Density 0.053%

    No Known Activations