© 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. 59248
    Prev
    Next
    INDEX
    Explanations

    village

    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
    뒤
    -0.79
    orology
    -0.74
    ený
    -0.73
    ੌ
    -0.73
     cathédrale
    -0.70
     ObjectMapper
    -0.70
    ెక్
    -0.69
     headquartered
    -0.68
    tigkeit
    -0.68
    carbox
    -0.68
    POSITIVE LOGITS
     village
    6.81
     villages
    5.44
    village
    5.09
     Village
    4.97
    Village
    4.91
    村
    4.22
     VILLAGE
    4.22
     villagers
    3.98
     Villages
    3.80
    VILL
    2.94
    Activations Density 0.118%

    No Known Activations