© 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. 107306
    Prev
    Next
    INDEX
    Explanations

    Rockford area locations

    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
    Jewish
    -0.75
    ivka
    -0.72
     Jewish
    -0.72
    🎉
    -0.72
     cópia
    -0.71
     Praha
    -0.71
    𝐆
    -0.68
    datepicker
    -0.68
    厘米
    -0.67
     đua
    -0.67
    POSITIVE LOGITS
     Rockford
    1.07
    magne
    0.88
     Freeport
    0.88
    Dexter
    0.75
    ースター
    0.74
     سنگ
    0.73
     Buss
    0.73
    얀
    0.73
     replenish
    0.72
    pone
    0.71
    Activations Density 0.015%

    No Known Activations