© 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. 22-GEMMASCOPE-RES-131K
    7. 11166
    Prev
    Next
    INDEX
    Explanations

    order KETOFEN online

    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_22/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
     Anggota
    -1.20
     sué
    -1.04
     espagnol
    -1.03
    vergleich
    -1.01
     Američ
    -0.99
    頂いた
    -0.98
     生命周期
    -0.98
    ということは
    -0.97
    なー
    -0.97
    Loai
    -0.97
    POSITIVE LOGITS
    】
    1.09
     ‚
    1.07
    rature
    1.02
    ření
    1.01
    )">
    1.00
    ĩ
    1.00
    如果你
    0.99
    стройка
    0.96
     obses
    0.95
    IDAD
    0.93
    Activations Density 0.000%

    No Known Activations