© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43468
    Prev
    Next
    INDEX
    Explanations

    shoreline and coastline

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

    This neuron strongly activates on tokens containing the substring “line” (e.g. shoreline, coastline, timeline, water-line).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     There
    -2.92
     Though
    -2.88
     Despite
    -2.86
     Although
    -2.80
    Despite
    -2.70
     Undoubtedly
    -2.67
     During
    -2.53
     Shortly
    -2.52
     Perhaps
    -2.47
     Being
    -2.42
    POSITIVE LOGITS
    神
    2.91
    柺
    2.83
    䊏
    2.80
    媗
    2.70
    ⌵
    2.64
    ſſen
    2.61
    ༀ
    2.52
    
    2.52
     可愛い
    2.50
     trám
    2.50
    Activations Density 0.002%

    No Known Activations