© 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. 33369
    Prev
    Next
    INDEX
    Explanations

    meta http-equiv="X-UA-Compatible" content="IE=edge

    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
     meur
    -0.80
    オリジナル
    -0.75
    fence
    -0.75
     Originals
    -0.72
    Ори
    -0.68
     penonton
    -0.68
    Сем
    -0.68
    TRY
    -0.66
    dbl
    -0.65
    Исто
    -0.65
    POSITIVE LOGITS
     industry
    0.73
    traffic
    0.72
    刷新
    0.69
     Bura
    0.68
     bewilder
    0.68
    ㄡ
    0.68
    uitton
    0.68
    抵抗
    0.67
    ╗
    0.67
    Industry
    0.66
    Activations Density 0.072%

    No Known Activations