© 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. 73844
    Prev
    Next
    INDEX
    Explanations

    common schools, roughly delineated, sand ridge

    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
    ꧂
    -0.89
     Kenyans
    -0.87
    дкой
    -0.84
     while
    -0.80
    akses
    -0.77
     Purchase
    -0.77
     horrific
    -0.77
     ditangkap
    -0.77
    Chico
    -0.76
    ضور
    -0.75
    POSITIVE LOGITS
    好吃的
    0.93
     Labor
    0.90
    まりました
    0.85
    hej
    0.85
     molti
    0.84
     Dider
    0.84
     revered
    0.83
     labor
    0.82
    slightly
    0.81
     못
    0.80
    Activations Density 0.002%

    No Known Activations