© 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. 10-GEMMASCOPE-RES-131K
    7. 111112
    Prev
    Next
    INDEX
    Explanations

    land and shore

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

    The neuron fires on words describing land‐ or shore‐related context (e.g. land, landfall, shore, onshore, coastal).

    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
    嶮
    -1.66
    鼍
    -1.60
     uby
    -1.55
    羮
    -1.54
    鮰
    -1.48
    getragen
    -1.41
    
    -1.41
    鮸
    -1.40
    蛩
    -1.39
    ⚌
    -1.36
    POSITIVE LOGITS
    ⻄
    1.66
    (
    1.56
     from
    1.55
    近年
    1.49
     after
    1.45
    屋外
    1.27
     adjour
    1.27
     suele
    1.27
    日本人
    1.27
     altering
    1.26
    Activations Density 0.018%

    No Known Activations