© 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. 7268
    Prev
    Next
    INDEX
    Explanations

    sub-Saharan Africa and sub-parts

    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
    Brothers
    -0.78
     hall
    -0.76
     dad
    -0.76
    头的
    -0.72
     cypress
    -0.71
    AÇÃO
    -0.71
     Brothers
    -0.71
    ajima
    -0.70
    сах
    -0.69
    merzen
    -0.69
    POSITIVE LOGITS
    idiary
    0.91
    mper
    0.75
     energia
    0.75
    ddle
    0.74
    дия
    0.74
     cherche
    0.73
    %%%%%%%%
    0.72
     chieftain
    0.72
     използ
    0.72
     powie
    0.72
    Activations Density 0.057%

    No Known Activations