© 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. 90244
    Prev
    Next
    INDEX
    Explanations

    data protection and privacy

    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
     свер
    -0.82
    素晴
    -0.81
    喫
    -0.80
    いえば
    -0.77
    に戻る
    -0.77
     honored
    -0.76
    しましょう
    -0.74
     Esper
    -0.74
     Utili
    -0.74
    nterior
    -0.72
    POSITIVE LOGITS
    ICO
    1.16
    cales
    1.02
    Schedule
    0.88
     ICO
    0.88
    Column
    0.88
    Processing
    0.86
     kush
    0.85
    ię
    0.85
    LEY
    0.84
    mathrm
    0.84
    Activations Density 0.008%

    No Known Activations