© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102492
    Prev
    Next
    INDEX
    Explanations

    money and financial transactions

    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
    嫫
    -1.70
    </b>
    -1.68
    </sup>
    -1.64
     ás
    -1.61
    </h2>
    -1.61
     fairly
    -1.59
    injured
    -1.59
    _
    -1.56
     empie
    -1.55
    piecze
    -1.52
    POSITIVE LOGITS
     to
    2.34
     They
    1.60
     and
    1.59
     ausdrück
    1.57
     Their
    1.48
    .
    1.47
    或者
    1.46
    鷭
    1.42
     หรือ
    1.39
     разнообраз
    1.37
    Activations Density 0.012%

    No Known Activations