© 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. 33464
    Prev
    Next
    INDEX
    Explanations

    municipality and prefecture names

    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
     Bak
    -0.81
    Std
    -0.77
    嵯
    -0.75
     NSError
    -0.74
    pses
    -0.73
    TITLE
    -0.72
     PEI
    -0.71
    Bak
    -0.69
    驳
    -0.69
     Companies
    -0.69
    POSITIVE LOGITS
     ordinance
    0.89
     city
    0.84
    Morte
    0.80
     municipal
    0.76
     Ordinance
    0.74
     residents
    0.74
     disabling
    0.73
    립
    0.73
     disable
    0.71
    odrome
    0.70
    Activations Density 0.036%

    No Known Activations