© 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. 103427
    Prev
    Next
    INDEX
    Explanations

    one or singular events

    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
     seuls
    -1.21
    ⅗
    -1.12
     entweder
    -1.09
     još
    -1.08
     především
    -1.06
     hlavně
    -1.06
     eerste
    -1.03
    al
    -1.02
    ∛
    -1.02
    wens
    -1.01
    POSITIVE LOGITS
     one
    8.06
     одна
    3.58
     одного
    3.53
    One
    3.53
     один
    3.23
    หนึ่ง
    3.20
     одной
    3.16
    有一天
    3.06
     одну
    3.06
     egyik
    3.05
    Activations Density 0.069%

    No Known Activations