© 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. 128624
    Prev
    Next
    INDEX
    Explanations

    business, legal, and financial terms

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

    manufacturing, classification, government, country

    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
     отсут
    0.55
     alegría
    0.50
     pensamientos
    0.48
     увидеть
    0.48
    защи
    0.47
    曇
    0.46
     বাণী
    0.45
    ष्ण
    0.44
     отсутствие
    0.44
     Beschäft
    0.44
    POSITIVE LOGITS
     本
    0.57
     公司
    0.51
    টর
    0.50
    <0x84>
    0.47
     特
    0.47
     ブリヂストン
    0.47
     政府
    0.47
     如果
    0.47
     这个
    0.47
     事
    0.46
    Activations Density 0.000%

    No Known Activations