© 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. 34-GEMMASCOPE-RES-131K
    7. 7300
    Prev
    Next
    INDEX
    Explanations

    vim, Michigan, Melbourne

    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
     Parla
    -0.80
     пери
    -0.77
     polyn
    -0.74
    ág
    -0.74
    krb
    -0.72
     Yak
    -0.70
    陸上
    -0.68
    pk
    -0.68
    ͂
    -0.66
     feels
    -0.66
    POSITIVE LOGITS
    Michigan
    1.20
    Detroit
    1.20
     Detroit
    1.15
     Michigan
    1.05
    vim
    1.02
     Vim
    0.98
    Melbourne
    0.97
     Geelong
    0.97
     Melbourne
    0.96
     vim
    0.96
    Activations Density 0.043%

    No Known Activations