© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 181723
    Prev
    Next
    INDEX
    Explanations

    municipal funds and non-English characters

    np_acts-logits-general · gemini-2.5-flash-lite

    word or phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Management
    0.50
     production
    0.50
     _
    0.48
     management
    0.48
     dure
    0.47
    _{
    0.46
     sur
    0.46
     taglio
    0.46
     Timur
    0.45
     Timor
    0.45
    POSITIVE LOGITS
    椇
    0.54
    funds
    0.50
    鹄
    0.49
     रम
    0.49
     చరిత్ర
    0.49
    municipal
    0.49
    नरी
    0.49
    纪念
    0.48
    ೋಜನ
    0.48
     चैंप
    0.48
    Activations Density 0.000%

    No Known Activations