© 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. 187516
    Prev
    Next
    INDEX
    Explanations

    investment advisory and management

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

    definitions and explanations

    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
     graphs
    0.49
    趄
    0.48
     catechol
    0.47
     isomeric
    0.47
     thoracic
    0.46
     trifle
    0.46
     diffus
    0.45
     bactéri
    0.44
    ropower
    0.44
     insuffis
    0.43
    POSITIVE LOGITS
     並
    0.56
     展示
    0.52
     フランス
    0.52
     海外
    0.50
     保護
    0.50
     不要
    0.49
     Великобрита
    0.48
     長
    0.48
     スペ
    0.48
     スマ
    0.47
    Activations Density 0.001%

    No Known Activations