© 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. 10-GEMMASCOPE-RES-131K
    4. 118805
    Prev
    Next
    INDEX
    Explanations

    transaction costs and types

    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_10/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
    </strong>
    -2.52
    鲧
    -2.22
     of
    -2.20
     accentu
    -2.08
     are
    -2.06
     serão
    -1.98
     accentuated
    -1.93
     ビキニ
    -1.93
     precludes
    -1.91
    凩
    -1.91
    POSITIVE LOGITS
    したので
    2.13
    してます
    2.03
    倶
    1.95
    </h5>
    1.84
    transaction
    1.81
    مرة
    1.80
     zijn
    1.78
    just
    1.78
     zelo
    1.75
    するので
    1.75
    Activations Density 0.009%

    No Known Activations