© 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. 89793
    Prev
    Next
    INDEX
    Explanations

    local history and historical places

    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
    anglès
    -0.78
    外国人
    -0.77
     wojsk
    -0.77
    店長
    -0.75
    地下鉄
    -0.74
    冒険
    -0.74
    poids
    -0.73
     بالع
    -0.71
     Lehre
    -0.71
     mechanics
    -0.70
    POSITIVE LOGITS
     history
    1.31
    local
    1.22
     ιστο
    1.20
     histories
    1.14
     historia
    1.14
     historical
    1.10
    Local
    1.08
     historian
    1.07
    hist
    1.05
     historians
    1.05
    Activations Density 0.007%

    No Known Activations