© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 33422
    Prev
    Next
    INDEX
    Explanations

    money laundering deal kickbacks contracts

    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
    ׇ
    -1.85
    ֩
    -1.55
     will
    -1.46
    ֺ
    -1.39
     chré
    -1.38
     блюдо
    -1.38
    oweit
    -1.30
     informaci
    -1.27
     چربی
    -1.27
    ἵ
    -1.27
    POSITIVE LOGITS
    ּוֹ
    1.61
    书房
    1.46
     السياس
    1.40
     oreilles
    1.34
    べし
    1.30
    וּ
    1.25
    ַּ
    1.24
    了不少
    1.24
     bepaalde
    1.23
    卧室
    1.22
    Activations Density 0.022%

    No Known Activations