© 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. 75651
    Prev
    Next
    INDEX
    Explanations

    bribes or commissions

    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
    精灵
    -0.82
     拼
    -0.79
    Оп
    -0.78
     ensi
    -0.78
    “……”
    -0.77
     kei
    -0.77
     Ema
    -0.75
     プレス
    -0.75
     rita
    -0.74
     Brems
    -0.74
    POSITIVE LOGITS
     gifts
    1.54
     gift
    1.23
    gifts
    1.20
     Gifts
    1.12
     kick
    1.05
     regalos
    1.04
    Gifts
    1.03
    Anything
    1.02
     anything
    0.99
     cadeaux
    0.95
    Activations Density 0.018%

    No Known Activations